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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تحميل
    -0.07
    /**↵↵
    -0.07
     Raq
    -0.07
    @Transactional
    -0.07
     protagonist
    -0.07
     Dimit
    -0.06
    尕
    -0.06
     spiral
    -0.06
    怯
    -0.06
    (Blueprint
    -0.06
    POSITIVE LOGITS
     '>
    0.09
    нал
    0.08
    พฤศ
    0.07
     lar
    0.06
     US
    0.06
    yped
    0.06
     analyze
    0.06
    _kw
    0.06
    ج
    0.06
    igs
    0.06
    Act Density 0.009%

    No Known Activations