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

    Neuronpedia

    INDEX
    Explanations

    normalize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأف
    -0.07
    446
    -0.07
     sevent
    -0.06
     childhood
    -0.06
     místa
    -0.06
     Liu
    -0.06
    ChangeEvent
    -0.06
     кни
    -0.06
    _td
    -0.06
    цвет
    -0.06
    POSITIVE LOGITS
     normalized
    0.07
    اده
    0.07
    eneric
    0.07
    ARATION
    0.07
    awi
    0.06
    .GetAxis
    0.06
    ~↵↵
    0.06
    ّم
    0.06
    ]
↵
    0.06
    ]}
    0.06
    Act Density 0.006%

    No Known Activations