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

    Neuronpedia

    INDEX
    Explanations

    .arange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UFF
    -0.08
     znalaz
    -0.07
     bigot
    -0.07
    URRE
    -0.07
    初衷
    -0.07
    apiro
    -0.07
    不懂
    -0.07
     וכמובן
    -0.06
    uddle
    -0.06
     فلا
    -0.06
    POSITIVE LOGITS
    是个
    0.08
     Series
    0.07
     +↵↵
    0.07
     Edited
    0.07
    monds
    0.07
    הפ
    0.06
     ClassName
    0.06
    gv
    0.06
    iOS
    0.06
    Ｓ
    0.06
    Act Density 0.006%

    No Known Activations