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

    Neuronpedia

    INDEX
    Explanations

    defining or summarizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스럽
    1.61
     স্বাধীনতা
    1.60
     желательно
    1.56
    ました
    1.53
    к
    1.50
     blisters
    1.50
     haunts
    1.48
     Bless
    1.48
    h
    1.47
     laurels
    1.45
    POSITIVE LOGITS
    nel
    1.63
    aan
    1.61
     ஒரு
    1.60
    operasi
    1.58
    ingen
    1.52
     vraag
    1.49
    ﺢ
    1.49
    তু
    1.47
    ører
    1.47
     говоря
    1.46
    Act Density 0.666%

    No Known Activations