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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buf
    -0.07
    уп
    -0.06
     nesting
    -0.06
     APPLICATION
    -0.06
     Ibid
    -0.06
     해결
    -0.06
    kol
    -0.06
     vz
    -0.06
    由
    -0.06
     comercial
    -0.06
    POSITIVE LOGITS
    ayım
    0.07
    _male
    0.07
    laden
    0.07
    irms
    0.06
    EVENT
    0.06
    /web
    0.06
    Jake
    0.06
     Fired
    0.06
    WhiteSpace
    0.06
    oter
    0.06
    Act Density 0.077%

    No Known Activations