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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nothing
    -0.07
     units
    -0.07
     расстоя
    -0.07
     Holding
    -0.07
    _recovery
    -0.06
    ¯¯
    -0.06
    営
    -0.06
     Gy
    -0.06
     scales
    -0.06
     sluts
    -0.06
    POSITIVE LOGITS
     as
    0.09
     ως
    0.06
    الله
    0.06
     regardless
    0.06
    اسي
    0.06
    ipt
    0.06
    ゲ
    0.06
     응
    0.06
     fig
    0.06
    فران
    0.06
    Act Density 0.021%

    No Known Activations