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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paras
    -0.07
     Amend
    -0.07
     EAST
    -0.06
    ponential
    -0.06
    .forms
    -0.06
    하여
    -0.06
    /std
    -0.06
     blooms
    -0.06
    率
    -0.06
    ates
    -0.06
    POSITIVE LOGITS
     Кон
    0.07
    νή
    0.06
    Fa
    0.06
    ắt
    0.06
    apeut
    0.06
     inevitably
    0.06
     Investig
    0.06
    .reactivex
    0.06
     introduce
    0.06
     네이트
    0.06
    Act Density 0.047%

    No Known Activations