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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illard
    -0.07
    $is
    -0.07
    ственные
    -0.07
    /AIDS
    -0.07
    chl
    -0.07
     daň
    -0.07
    رت
    -0.07
    opus
    -0.07
    anti
    -0.07
    Curve
    -0.06
    POSITIVE LOGITS
    .wrap
    0.07
     застос
    0.07
     beim
    0.06
     rusty
    0.06
    ,...
    0.06
     impressed
    0.05
     Paolo
    0.05
    -save
    0.05
     denies
    0.05
    ystick
    0.05
    Act Density 0.050%

    No Known Activations