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

    Neuronpedia

    INDEX
    Explanations

    f-string error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scalar
    0.90
     ]);
    0.88
    icaria
    0.85
    ]);}
    0.80
    rinsim
    0.77
     scalars
    0.77
     CtApp
    0.77
    xspace
    0.76
    ironolactone
    0.75
     ecmaVersion
    0.75
    POSITIVE LOGITS
    Pok
    0.94
    Casino
    0.91
     Pok
    0.85
    Live
    0.78
    、【
    0.77
    "
    0.75
    Play
    0.73
     slot
    0.73
    )'
    0.73
    slot
    0.73
    Act Density 0.070%

    No Known Activations