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

    Neuronpedia

    INDEX
    Explanations

    the number 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '،
    0.42
    '%(
    0.39
    ः
    0.38
    '";
    0.37
    льше
    0.36
    حد
    0.35
    mergeddata
    0.35
    деся
    0.35
    ものは
    0.35
     zet
    0.34
    POSITIVE LOGITS
    at
    0.56
    in
    0.54
    na
    0.49
    9
    0.49
    m
    0.48
    of
    0.43
    자
    0.43
    ف
    0.42
    ج
    0.40
    av
    0.40
    Act Density 0.004%

    No Known Activations