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

    Neuronpedia

    INDEX
    Explanations

    legal obligations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lord
    -0.84
    Lord
    -0.77
     liability
    -0.70
     liabilities
    -0.66
     broad
    -0.65
    HtmlAttribute
    -0.61
    Liability
    -0.61
     Liability
    -0.60
    UnknownFields
    -0.60
     Pea
    -0.59
    POSITIVE LOGITS
    s
    0.56
    shield
    0.51
     Мексичка
    0.50
    ships
    0.49
    scape
    0.49
     departement
    0.49
     marcadas
    0.49
     ква
    0.48
    новниш
    0.48
    sticks
    0.48
    Act Density 0.087%

    No Known Activations