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

    Neuronpedia

    INDEX
    Explanations

    precise calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assumed
    0.45
     assessed
    0.38
     enough
    0.38
    0.38
     adult
    0.37
     Bold
    0.37
     बोल्ड
    0.37
     উপসর্গ
    0.37
    キーワード
    0.37
    bold
    0.36
    POSITIVE LOGITS
     exact
    0.95
    Exact
    0.91
     exacte
    0.90
     Exact
    0.88
    精确
    0.86
    exact
    0.85
     precise
    0.82
     دقیق
    0.82
     точно
    0.78
     dokład
    0.78
    Act Density 0.000%

    No Known Activations