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

    Neuronpedia

    INDEX
    Explanations

    code, data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.61
    toThrow
    -0.50
    AutoSize
    -0.49
     هيا
    -0.48
    UrlResolution
    -0.48
    segu
    -0.47
     facie
    -0.47
    Suara
    -0.47
    onAttach
    -0.47
    GPC
    -0.47
    POSITIVE LOGITS
     Bar
    0.90
     bar
    0.89
    bar
    0.83
    Bar
    0.82
     barons
    0.82
    BAR
    0.79
     BAR
    0.76
    baron
    0.74
     baron
    0.71
     Baron
    0.69
    Act Density 0.008%

    No Known Activations