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

    Neuronpedia

    INDEX
    Explanations

    department of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.93
    et
    0.79
     R
    0.79
    _
    0.77
    op
    0.77
    oj
    0.77
     set
    0.77
     x
    0.76
     X
    0.75
    n
    0.75
    POSITIVE LOGITS
    <unused94>
    0.94
     ponctués
    0.89
    게요
    0.88
     faptul
    0.87
    先日
    0.86
    Ꮀ
    0.86
    ❓
    0.86
    ␊
    0.85
    ゲーム
    0.84
    ಶ್ರೀ
    0.84
    Act Density 0.004%

    No Known Activations