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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bezpeč
    -0.06
    τας
    -0.06
    ZO
    -0.06
     varies
    -0.06
    _duplicate
    -0.06
     BP
    -0.06
    Safety
    -0.06
    .tar
    -0.06
     Certification
    -0.06
    .screen
    -0.06
    POSITIVE LOGITS
    紅
    0.07
    /oauth
    0.07
     Ảnh
    0.07
     onu
    0.07
     öden
    0.07
     Fetish
    0.07
     kırmızı
    0.07
    (history
    0.06
    elligent
    0.06
    .")↵
    0.06
    Act Density 0.006%

    No Known Activations