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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on the present‐tense forms of the verb “to be” (e.g. “is,” “are”) that link a subject to its description.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lehr
    -0.07
    +"'
    -0.07
    294
    -0.06
     setContent
    -0.06
     Keep
    -0.06
     україн
    -0.06
     Between
    -0.06
    308
    -0.06
     zou
    -0.06
    .isNotBlank
    -0.06
    POSITIVE LOGITS
    AppName
    0.07
     recogn
    0.07
     disposing
    0.06
    odom
    0.06
    .where
    0.06
     manera
    0.06
    _picture
    0.06
     variance
    0.06
     nick
    0.06
     operand
    0.06
    Act Density 0.032%

    No Known Activations