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

    Neuronpedia

    INDEX
    Explanations

    relationship details or event items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     :");
    0.33
    ებისა
    0.31
    └──
    0.31
    ൊന്നും
    0.30
    क्सीडेंट
    0.29
     һәм
    0.28
     bzw
    0.28
    และการ
    0.27
    |");
    0.27
    上也
    0.27
    POSITIVE LOGITS
    ،
    0.93
    、
    0.90
    ፣
    0.88
    ,
    0.86
    ၊
    0.85
    ，
    0.77
     ፣
    0.74
     ,
    0.70
    ,,
    0.63
     ،
    0.62
    Act Density 0.683%

    No Known Activations