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

    Neuronpedia

    INDEX
    Explanations

    game loop variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stargo
    0.50
     ایم
    0.46
     قد
    0.45
    шками
    0.45
    ꞎ
    0.44
    メール
    0.44
    rfc
    0.44
    idagi
    0.43
    𐰣
    0.43
     Και
    0.42
    POSITIVE LOGITS
    ed
    0.43
    '],
    0.43
    \_
    0.42
    -
    0.42
    $',
    0.41
    Mat
    0.41
    AK
    0.41
     BULL
    0.40
    ',(
    0.40
     экономической
    0.39
    Act Density 0.000%

    No Known Activations