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

    Neuronpedia

    INDEX
    Explanations

    case for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تي
    0.55
    the
    0.46
    I
    0.45
    t
    0.43
    tk
    0.43
    Review
    0.43
    tx
    0.42
    tidak
    0.42
    n
    0.42
     روشن
    0.42
    POSITIVE LOGITS
    ್ಯಾ
    0.47
     parody
    0.47
    ！！！
    0.46
     Stroke
    0.44
    AssetDiscovery
    0.43
    ！）
    0.43
     Česk
    0.43
     LDS
    0.42
    ）」
    0.42
    ெடு
    0.42
    Act Density 0.005%

    No Known Activations