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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monitoring
    -0.07
     Ara
    -0.07
     tvá
    -0.07
    وروب
    -0.07
    .Arrays
    -0.07
    oreach
    -0.06
     renewal
    -0.06
    やる
    -0.06
     Lance
    -0.06
     sinister
    -0.06
    POSITIVE LOGITS
    €™
    0.06
    ıl
    0.06
    lej
    0.06
    당
    0.06
     bitwise
    0.06
    _TRANSFER
    0.06
    各
    0.06
    ELY
    0.06
     fights
    0.06
    �t
    0.06
    Act Density 0.009%

    No Known Activations