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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaps
    -0.07
    vehicle
    -0.07
     hint
    -0.07
    elfth
    -0.07
     tread
    -0.07
     Sight
    -0.07
     gradient
    -0.07
    觸
    -0.07
    度
    -0.07
    acakt
    -0.07
    POSITIVE LOGITS
    疙
    0.08
    מנה
    0.07
    ){}↵
    0.07
    Центр
    0.07
     dysfunctional
    0.07
    坨
    0.07
    最适合
    0.07
    ペ
    0.07
     ]↵↵
    0.06
    建国
    0.06
    Act Density 0.003%

    No Known Activations