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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kingdoms
    -0.06
     cultures
    -0.06
    (signature
    -0.06
    asmus
    -0.06
     Sometimes
    -0.06
     holiday
    -0.06
    /logging
    -0.06
     sca
    -0.06
    ,f
    -0.06
    apes
    -0.06
    POSITIVE LOGITS
     vriend
    0.07
    .hxx
    0.06
    오는
    0.06
     Greenville
    0.06
    ww
    0.06
    ickou
    0.06
     Elena
    0.06
     پرو
    0.06
     oyuncu
    0.06
    息
    0.06
    Act Density 0.000%

    No Known Activations