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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <strong>
    0.80
    //
    0.73
    <b>
    0.62
    직
    0.62
    hed
    0.61
     –
    0.59
    hes
    0.59
    en
    0.59
    hips
    0.59
     bits
    0.58
    POSITIVE LOGITS
     Uncomment
    1.24
     yalnızca
    1.21
     aumenta
    1.17
     hinzuf
    1.16
     adicion
    1.16
    呻
    1.13
    matplotlib
    1.12
     指定
    1.11
     添加
    1.10
    指定的
    1.09
    Act Density 0.017%

    No Known Activations