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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captures
    -0.07
     muss
    -0.07
    ёл
    -0.07
    たら
    -0.06
     pencil
    -0.06
     fret
    -0.06
    .vec
    -0.06
     rec
    -0.06
     manages
    -0.06
     EL
    -0.06
    POSITIVE LOGITS
     Covent
    0.07
    ї
    0.07
     forState
    0.07
    .Gson
    0.07
     диамет
    0.07
    Formatter
    0.06
     }}"></
    0.06
    Information
    0.06
    wingConstants
    0.06
    ськ
    0.06
    Act Density 0.013%

    No Known Activations