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

    Neuronpedia

    INDEX
    Explanations

    1-866-488-7386

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LLCATS
    0.63
     gall
    0.62
     eyebrow
    0.61
     প্রতিষ্ঠান
    0.60
     keres
    0.58
    iodo
    0.58
     haystack
    0.58
     eyebrows
    0.57
    vané
    0.57
    omyces
    0.57
    POSITIVE LOGITS
    INET
    0.61
     απ
    0.57
    ப்பெ
    0.56
     Ab
    0.55
     Dep
    0.53
     ダウン
    0.53
     μετα
    0.52
     положи
    0.52
     فوټبال
    0.52
     Filling
    0.52
    Act Density 0.264%

    No Known Activations