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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    td
    -0.06
    葉
    -0.06
     cliffs
    -0.06
    �
    -0.06
     disp
    -0.06
    castle
    -0.06
    semi
    -0.06
    敢
    -0.06
     strugg
    -0.06
     tools
    -0.06
    POSITIVE LOGITS
     GPI
    0.08
     boğ
    0.07
     RETURN
    0.07
    렸다
    0.06
    endet
    0.06
    lında
    0.06
     WAL
    0.06
    führt
    0.06
    зано
    0.06
     причины
    0.06
    Act Density 0.014%

    No Known Activations