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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    塑胶
    -0.08
     video
    -0.08
     Shah
    -0.07
    -secret
    -0.07
    版权所有
    -0.07
     edt
    -0.07
     inflate
    -0.07
    licensed
    -0.07
     ries
    -0.07
     Совет
    -0.07
    POSITIVE LOGITS
     matchmaking
    0.08
    ♯
    0.07
    柬
    0.07
    ⇛
    0.07
    —↵↵
    0.07
    プラス
    0.07
    הוצאה
    0.07
    ählt
    0.07
    键
    0.06
     Symposium
    0.06
    Act Density 0.009%

    No Known Activations