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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens naming consumable substances—i.e. ingredients or food items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     завод
    -0.07
    ordes
    -0.07
    elsius
    -0.07
     -(
    -0.07
     temperatura
    -0.07
     lim
    -0.06
    =e
    -0.06
    	rows
    -0.06
     XI
    -0.06
    OfWeek
    -0.06
    POSITIVE LOGITS
     inplace
    0.07
    稍
    0.07
    than
    0.06
     prin
    0.06
     účin
    0.06
    .Up
    0.06
    FH
    0.06
    -disable
    0.06
    _mem
    0.06
    };↵↵
    0.06
    Act Density 0.158%

    No Known Activations