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
     bao
    0.48
     Webster
    0.42
     தீங்கு
    0.42
     Mục
    0.41
     adam
    0.39
     podm
    0.39
     Linton
    0.39
     Judy
    0.38
     wherein
    0.38
     Dent
    0.38
    POSITIVE LOGITS
    ...*/
    0.46
    <b>
    0.44
    ada
    0.41
    зна
    0.41
     अक्सर
    0.41
    est
    0.41
    З
    0.41
    {//
    0.40
     trä
    0.39
    िंग
    0.39
    Act Density 0.084%

    No Known Activations