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

    Neuronpedia

    INDEX
    Explanations

    examples or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    를
    1.29
    やかな
    1.24
    的
    1.21
    anlage
    1.19
    ${\
    1.17
     rač
    1.09
     های
    1.09
    urally
    1.09
    ด้วย
    1.08
    我们就
    1.08
    POSITIVE LOGITS
    coating
    2.08
    coat
    1.96
    Gmail
    1.74
    罪
    1.73
    thag
    1.72
     toss
    1.70
     though
    1.69
    stoi
    1.68
    gson
    1.67
    sworth
    1.65
    Act Density 0.035%

    No Known Activations