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

    Neuronpedia

    INDEX
    Explanations

    user prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.92
    emale
    0.79
    AYLOR
    0.78
    بال
    0.73
    на
    0.72
    之间
    0.71
    在于
    0.71
                                   
    0.70
     Федера
    0.70
     Remains
    0.70
    POSITIVE LOGITS
    ס
    1.38
     brawl
    1.01
     sợ
    0.98
     ovog
    0.94
    िग
    0.93
    ओ
    0.93
     faça
    0.92
     awali
    0.90
    ス
    0.88
     endoscopy
    0.88
    Act Density 0.029%

    No Known Activations