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

    Neuronpedia

    INDEX
    Explanations

    . following sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Piers
    0.44
    త్
    0.43
     স্বয়ং
    0.42
    INDER
    0.40
    หรือไม่
    0.39
    Coins
    0.38
    替换
    0.38
    謎
    0.38
     Poles
    0.38
     Coins
    0.38
    POSITIVE LOGITS
    izing
    0.45
    enca
    0.43
    č
    0.43
    ப்ப
    0.42
    ensem
    0.41
    indent
    0.41
    au
    0.41
    éri
    0.41
    ativ
    0.40
    ilen
    0.40
    Act Density 0.012%

    No Known Activations