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

    Neuronpedia

    INDEX
    Explanations

    margin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vegan
    -0.07
    σσα
    -0.07
     palabras
    -0.06
     далі
    -0.06
     liken
    -0.06
    adero
    -0.06
    UMB
    -0.06
     руках
    -0.06
    Roger
    -0.06
     vẽ
    -0.06
    POSITIVE LOGITS
    ']]]↵
    0.06
    .@
    0.06
    .defaultProps
    0.06
     Stephens
    0.06
     Require
    0.06
     Sag
    0.06
     Parents
    0.06
    дов
    0.06
    nímu
    0.06
     Kag
    0.06
    Act Density 0.007%

    No Known Activations