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

    Neuronpedia

    INDEX
    Explanations

    drivers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     влад
    -0.07
    ら
    -0.07
     Parent
    -0.07
    .maxLength
    -0.07
    천
    -0.06
     Duel
    -0.06
    amen
    -0.06
     provoke
    -0.06
    онь
    -0.06
     cela
    -0.06
    POSITIVE LOGITS
    !',↵
    0.06
    STITUTE
    0.06
    ือก
    0.06
     classification
    0.06
    (transaction
    0.06
     intimately
    0.06
    (code
    0.06
    .Condition
    0.06
    .atomic
    0.06
    AUTHORIZED
    0.06
    Act Density 0.033%

    No Known Activations