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

    Neuronpedia

    INDEX
    Explanations

    permission

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claramente
    -0.08
     понятно
    -0.08
     seguramente
    -0.08
    bedarf
    -0.08
     स्पष्ट
    -0.08
     ясно
    -0.08
     natürlichen
    -0.08
     Trends
    -0.07
     claras
    -0.07
     claros
    -0.07
    POSITIVE LOGITS
     dürfen
    0.12
     permissible
    0.11
     permitted
    0.11
     darf
    0.11
     durfte
    0.10
    Allowed
    0.10
     participating
    0.10
     permitido
    0.10
     allowed
    0.09
     proceeding
    0.09
    Act Density 0.055%

    No Known Activations