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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bc
    -0.07
    طبيق
    -0.07
    Behind
    -0.07
    _BORDER
    -0.07
    투
    -0.06
    YPD
    -0.06
     Kathy
    -0.06
    rink
    -0.06
    indexed
    -0.06
    _nb
    -0.06
    POSITIVE LOGITS
    ur
    0.07
     excer
    0.06
    .club
    0.06
    fft
    0.06
    人员
    0.06
     inventions
    0.06
    .',↵
    0.06
     surviv
    0.06
    .legend
    0.06
     transf
    0.06
    Act Density 0.001%

    No Known Activations