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

    Neuronpedia

    INDEX
    Explanations

    email, URLs, or code paths

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs starting with https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.49
     än
    0.47
    ht
    0.47
    ai
    0.46
    vis
    0.43
    ität
    0.43
     exempel
    0.43
    ’
    0.43
     mäng
    0.43
    ia
    0.42
    POSITIVE LOGITS
    ל
    1.05
    ב
    0.96
    מ
    0.80
    י
    0.77
    ی
    0.77
    ע
    0.73
    אם
    0.73
    یت
    0.71
    し
    0.71
    ب
    0.69
    Act Density 0.014%

    No Known Activations