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

    Neuronpedia

    INDEX
    Explanations

    questions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBO
    -0.95
    resas
    -0.90
    caval
    -0.84
    ziplin
    -0.83
    laj
    -0.81
    늦
    -0.81
     GAB
    -0.79
    ⅲ
    -0.78
    adni
    -0.78
     fournis
    -0.78
    POSITIVE LOGITS
     partial
    0.88
    owią
    0.80
    ylim
    0.77
     until
    0.75
    partial
    0.73
    県立
    0.73
     getString
    0.72
    jusqu
    0.71
     that
    0.71
    Надо
    0.69
    Act Density 0.002%

    No Known Activations