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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ắp
    -0.07
     Alf
    -0.07
    例行
    -0.07
    _fatal
    -0.06
    午
    -0.06
    ／
    -0.06
     angular
    -0.06
    顶级
    -0.06
    pee
    -0.06
     forgetting
    -0.06
    POSITIVE LOGITS
    帖
    0.07
     pada
    0.07
    ına
    0.07
     Clintons
    0.07
    妻子
    0.07
    women
    0.07
    꿘
    0.07
    path
    0.06
     Streams
    0.06
    _PARAM
    0.06
    Act Density 0.014%

    No Known Activations