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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芙
    -0.07
    _GRAPH
    -0.07
     favors
    -0.07
     footsteps
    -0.06
     صاحب
    -0.06
     burdens
    -0.06
     paced
    -0.06
     LoginForm
    -0.06
     sleeping
    -0.06
     Savage
    -0.06
    POSITIVE LOGITS
     Ston
    0.07
     realpath
    0.07
     Мон
    0.07
    Mi
    0.07
    ?↵↵↵↵↵↵
    0.07
     dirección
    0.06
    Unicode
    0.06
     gql
    0.06
    安排
    0.06
    }elseif
    0.06
    Act Density 0.032%

    No Known Activations