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

    Neuronpedia

    INDEX
    Explanations

    awareness, knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suddenly
    -0.08
     показатели
    -0.08
     количе
    -0.08
     пациент
    -0.07
     конди
    -0.07
     измер
    -0.07
    screen
    -0.07
     удовлетвор
    -0.07
    Somos
    -0.07
     plötzlich
    -0.07
    POSITIVE LOGITS
     terror
    0.09
     wrongdoing
    0.08
     yon
    0.08
    涉嫌
    0.08
     Alameda
    0.08
     knowingly
    0.07
    _INTR
    0.07
     toxin
    0.07
    违反
    0.07
    恐
    0.07
    Act Density 0.018%

    No Known Activations