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

    Neuronpedia

    INDEX
    Explanations

    unus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pro
    -0.06
     sla
    -0.06
     thổ
    -0.06
     neighborhoods
    -0.06
    标题
    -0.06
     Lantern
    -0.06
     схем
    -0.06
    Ale
    -0.06
    汇
    -0.06
     offence
    -0.06
    POSITIVE LOGITS
     unus
    0.22
    WIN
    0.09
    &
    0.09
    win
    0.09
    기
    0.07
    ybrid
    0.06
    .tw
    0.06
     UNKNOWN
    0.06
    _UNICODE
    0.06
    нач
    0.06
    Act Density 0.003%

    No Known Activations