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

    Neuronpedia

    INDEX
    Explanations

    "'s" and "is"

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the present‐tense copula “is.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     foreach
    -0.08
    provide
    -0.07
    mith
    -0.06
     completo
    -0.06
    .','
    -0.06
     providing
    -0.06
     attention
    -0.06
    ordered
    -0.06
     bore
    -0.06
     fuck
    -0.06
    POSITIVE LOGITS
    Its
    0.07
    _SU
    0.07
    riger
    0.07
     Its
    0.07
    .ids
    0.07
     Applies
    0.07
     долж
    0.06
    unciation
    0.06
    Ｓ
    0.06
    Feels
    0.06
    Act Density 0.051%

    No Known Activations