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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _floor
    -0.08
     Kiss
    -0.07
    �
    -0.07
     Пос
    -0.07
    女性
    -0.07
    ivol
    -0.06
    acute
    -0.06
     vo
    -0.06
     Kansas
    -0.06
    AF
    -0.06
    POSITIVE LOGITS
    __));↵
    0.07
    (viewModel
    0.06
     نموده
    0.06
    ))))↵
    0.06
    '</
    0.06
    �
    0.06
    )))↵
    0.06
    ！');↵
    0.06
     معد
    0.06
    )((((
    0.06
    Act Density 0.153%

    No Known Activations