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

    Neuronpedia

    INDEX
    Explanations

    agent names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.51
    的
    0.51
    Dichloro
    0.49
    ).
    0.49
     GameObject
    0.48
    Versioning
    0.47
    Hei
    0.46
    庚
    0.45
    \;
    0.45
    $
    0.45
    POSITIVE LOGITS
    ardı
    0.51
     như
    0.49
     ಹೇಗೆ
    0.49
     bądź
    0.48
     ഞ
    0.48
     буль
    0.47
     ď
    0.47
     biceps
    0.47
    enek
    0.46
     vutta
    0.46
    Act Density 0.000%

    No Known Activations