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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thiệu
    -0.07
     הברית
    -0.07
     hatırla
    -0.07
    习近平总
    -0.07
     zza
    -0.07
    _RAD
    -0.07
    蠋
    -0.07
    /cards
    -0.07
     gıda
    -0.07
     Bryce
    -0.07
    POSITIVE LOGITS
     ·
    0.07
    ,<
    0.07
     Criterion
    0.07
    \<
    0.07
    Ver
    0.07
     �
    0.07
    	system
    0.07
    )\<
    0.07
     MX
    0.07
    📉
    0.07
    Act Density 0.000%

    No Known Activations