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

    Neuronpedia

    INDEX
    Explanations

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.87
    ↵↵↵↵
    0.77
    </tr>
    0.76
    ↵↵↵
    0.73
     eff
    0.72
    ↵↵↵↵↵
    0.71
     देत
    0.69
    뿐
    0.69
    ukti
    0.65
    ↵↵↵↵↵↵
    0.63
    POSITIVE LOGITS
    ‶
    0.94
     aslında
    0.91
    如果
    0.89
    返回
    0.89
     এই
    0.88
     返回
    0.86
    Bounded
    0.85
     وهي
    0.85
     "["
    0.84
     eğer
    0.84
    Act Density 0.143%

    No Known Activations