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

    Neuronpedia

    INDEX
    Explanations

    . , G ;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    되
    0.39
     maiores
    0.38
    碾
    0.38
    㧕
    0.37
    핏
    0.37
    庄
    0.37
    🍃
    0.36
    烈
    0.36
    ポール
    0.36
     Shutdown
    0.36
    POSITIVE LOGITS
    [,,"
    0.42
     посте
    0.42
    jee
    0.41
     общества
    0.40
     commenting
    0.39
     capitalism
    0.39
     συνέχ
    0.39
     ironing
    0.39
     consenting
    0.38
     prostitution
    0.37
    Act Density 0.000%

    No Known Activations