Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specificity limitations

    np_max-act · gemini-2.0-flash

    The neuron peaks on words that call out specificity or particularity (e.g. “specific,” “particular,” “local,” version labels).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions on genetic studies or analyses related to population structures and breeding behaviors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dressing
    -0.07
    (code
    -0.07
    506
    -0.06
     завтра
    -0.06
     constitutional
    -0.06
    ilet
    -0.06
     repeatedly
    -0.06
    _set
    -0.06
     Maria
    -0.06
     их
    -0.06
    POSITIVE LOGITS
     أن
    0.06
    ()>↵
    0.06
    _encrypt
    0.06
    Ext
    0.06
     seg
    0.06
     �
    0.06
    klad
    0.06
    entai
    0.06
    dire
    0.06
    dej
    0.06
    Act Density 0.138%

    No Known Activations