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

    Neuronpedia

    INDEX
    Explanations

    source code headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incons
    -0.06
    ["@
    -0.06
     кноп
    -0.06
     Μά
    -0.06
     det
    -0.06
    ायत
    -0.06
     bisc
    -0.06
     thinkers
    -0.06
    weakSelf
    -0.06
     landed
    -0.06
    POSITIVE LOGITS
     ประ
    0.07
    _voice
    0.07
     Thổ
    0.07
    ullo
    0.06
     �
    0.06
    ;,
    0.06
     waveform
    0.06
    :y
    0.06
     전체
    0.06
     ـ
    0.06
    Act Density 0.002%

    No Known Activations