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

    Neuronpedia

    INDEX
    Explanations

    Technical abbreviations/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ST
    -0.06
    στα
    -0.06
     keyof
    -0.06
    .getChannel
    -0.06
     되어
    -0.06
    recated
    -0.06
    ьи
    -0.06
    DECLARE
    -0.06
    封
    -0.06
     deprived
    -0.06
    POSITIVE LOGITS
    uction
    0.07
    _wp
    0.07
     muschi
    0.06
    uuml
    0.06
    orne
    0.06
     uncont
    0.06
    _cart
    0.06
     Memory
    0.06
     freak
    0.06
    _CHARACTER
    0.06
    Act Density 0.062%

    No Known Activations