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

    Neuronpedia

    INDEX
    Explanations

    being valued

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    0.82
    場合
    0.74
    s
    0.74
    開始
    0.70
     ମ
    0.64
    ⟥
    0.64
     Uses
    0.62
     ezzel
    0.62
    靗
    0.61
    úng
    0.61
    POSITIVE LOGITS
     in
    1.06
    在
    0.97
    ي
    0.97
    י
    0.93
    रा
    0.92
    ও
    0.92
     σε
    0.90
    ми
    0.89
    AD
    0.88
    س
    0.85
    Act Density 0.039%

    No Known Activations