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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Young
    -0.07
     потер
    -0.07
    फ
    -0.07
    _series
    -0.06
    чить
    -0.06
     Thông
    -0.06
    \DB
    -0.06
     preach
    -0.06
     eşit
    -0.06
    .hash
    -0.06
    POSITIVE LOGITS
     paci
    0.06
    Ignore
    0.06
    fb
    0.06
    สภ
    0.06
     겁
    0.06
    mouse
    0.06
     sun
    0.06
     ears
    0.06
     فيها
    0.06
    opause
    0.06
    Act Density 0.046%

    No Known Activations