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

    Neuronpedia

    INDEX
    Explanations

    technical terms with version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     、,
    0.44
    луйста
    0.42
    、、、
    0.41
     ,,
    0.41
    、​
    0.40
    লেম
    0.39
    ̺
    0.38
     sierp
    0.37
     ataupun
    0.37
    ﾝ
    0.37
    POSITIVE LOGITS
    6
    0.69
    7
    0.65
    9
    0.64
    2
    0.63
    5
    0.63
    1
    0.62
    3
    0.62
    8
    0.59
    ６
    0.58
    4
    0.56
    Act Density 0.079%

    No Known Activations