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

    Neuronpedia

    INDEX
    Explanations

    speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ::::::::::
    -0.08
     느
    -0.07
    extern
    -0.07
     hát
    -0.07
    據
    -0.07
    เท
    -0.07
     ль
    -0.06
     Partition
    -0.06
    ;/*
    -0.06
    เตร
    -0.06
    POSITIVE LOGITS
    .slides
    0.06
     міль
    0.06
    eeper
    0.06
    ypo
    0.06
     урож
    0.06
     Money
    0.06
    laş
    0.06
    .Global
    0.06
    .iloc
    0.06
    .Connect
    0.06
    Act Density 0.481%

    No Known Activations