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

    Neuronpedia

    INDEX
    Explanations

    Error, modus, conflict, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.72
    t
    0.71
    in
    0.64
    f
    0.63
    ل
    0.62
    ين
    0.60
    -
    0.59
    z
    0.59
    ку
    0.57
    el
    0.55
    POSITIVE LOGITS
     ၁
    0.53
     п
    0.51
    ،
    0.50
     quatro
    0.47
     ૧
    0.46
     ១
    0.46
     cinq
    0.46
     niektor
    0.45
     ١
    0.45
     negativos
    0.45
    Act Density 2.187%

    No Known Activations