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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron responds to list‐item markers—especially the numbers and trailing periods used in numbered lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     respect
    -0.07
    pickle
    -0.06
     CHANNEL
    -0.06
     qualquer
    -0.06
    TOTAL
    -0.06
     killings
    -0.06
     تجربه
    -0.06
    ================================================================
    -0.06
    porto
    -0.06
     Coming
    -0.06
    POSITIVE LOGITS
    (nullptr
    0.07
     cameo
    0.07
    duc
    0.07
    terraform
    0.06
     ř
    0.06
    ocu
    0.06
    ouse
    0.06
     CHtml
    0.06
    leted
    0.06
    Issuer
    0.06
    Act Density 0.030%

    No Known Activations