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

    Neuronpedia

    INDEX
    Explanations

    unauthorized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neu
    -0.08
     Chem
    -0.08
    .Param
    -0.07
     કુલ
    -0.07
     Saat
    -0.07
     Shock
    -0.07
     Resin
    -0.07
     Tipps
    -0.07
     Gesamt
    -0.07
    fol
    -0.07
    POSITIVE LOGITS
     unauthorized
    0.12
    Unauthorized
    0.11
     Unauthorized
    0.11
    侵犯
    0.10
     доступа
    0.09
     nominate
    0.09
     intrusion
    0.09
     privada
    0.09
    転載
    0.09
    アクセス
    0.08
    Act Density 0.006%

    No Known Activations