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

    Neuronpedia

    INDEX
    Explanations

    precise variation or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ापुर
    0.47
    Если
    0.42
    гка
    0.41
    если
    0.40
     ему
    0.39
    कई
    0.39
    зыка
    0.39
     comprendere
    0.38
    йно
    0.38
    த்துக்கும்
    0.38
    POSITIVE LOGITS
     själ
    0.41
     شرکت
    0.41
     company
    0.40
     spokes
    0.39
    经销
    0.39
     ജീ
    0.39
    uerre
    0.39
    atanga
    0.38
     turnaround
    0.38
    ذر
    0.37
    Act Density 0.002%

    No Known Activations