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

    Neuronpedia

    INDEX
    Explanations

    c++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NaOMe
    0.82
     abstracto
    0.82
     import
    0.80
     faça
    0.79
     abstrak
    0.79
    esterol
    0.78
    import
    0.77
    Chocolate
    0.76
     declare
    0.76
     पोषक
    0.75
    POSITIVE LOGITS
    int
    0.75
     Greenville
    0.74
    void
    0.72
     ow
    0.72
     void
    0.71
    template
    0.69
     jammed
    0.68
    VOID
    0.65
     int
    0.64
     Edmunds
    0.62
    Act Density 0.070%

    No Known Activations