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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quets
    -0.08
     דין
    -0.07
     inventory
    -0.07
     גופ
    -0.07
    Way
    -0.07
     ann
    -0.07
     לקרא
    -0.07
    alendar
    -0.07
     diagnostic
    -0.07
     자
    -0.07
    POSITIVE LOGITS
     СШ
    0.07
     philosophical
    0.07
     Limits
    0.07
    (__('
    0.06
     Barrel
    0.06
     Kön
    0.06
    -wide
    0.06
    加大
    0.06
     STEM
    0.06
     hopeless
    0.06
    Act Density 0.003%

    No Known Activations