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

    Neuronpedia

    INDEX
    Explanations

    Multiplying, Installing, Genuine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.47
    NEL
    0.46
    N
    0.46
    L
    0.45
    y
    0.45
    ORF
    0.44
    OU
    0.43
    i
    0.42
    Ｅ
    0.42
    STY
    0.41
    POSITIVE LOGITS
    钽
    0.52
    ními
    0.50
    ments
    0.49
    μένη
    0.46
    fohlen
    0.45
    ní
    0.44
    مة
    0.44
    lijke
    0.44
    nosť
    0.43
    ijn
    0.43
    Act Density 0.003%

    No Known Activations