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

    Neuronpedia

    INDEX
    Explanations

    cpuid, CainXPii, Pu'u, romanToInt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    0.59
    s
    0.59
    al
    0.58
    లో
    0.58
    ма
    0.55
    in
    0.54
     at
    0.53
    мери
    0.52
    د
    0.52
    ied
    0.52
    POSITIVE LOGITS
    る
    0.63
    на
    0.57
    고
    0.52
    ↵
    0.50
    ด์
    0.49
    ت
    0.48
    KeyDown
    0.47
    که
    0.47
    тна
    0.47
    די
    0.46
    Act Density 0.000%

    No Known Activations