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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    参
    -0.07
     Programs
    -0.07
     elk
    -0.07
     feeds
    -0.06
    idents
    -0.06
     Americans
    -0.06
     张
    -0.06
    ISA
    -0.06
    American
    -0.06
     staples
    -0.06
    POSITIVE LOGITS
     Vict
    0.08
    لف
    0.07
     оказ
    0.07
    Symbol
    0.06
     provozu
    0.06
    έ
    0.06
    Io
    0.06
    anye
    0.06
    .linkLabel
    0.06
    ленні
    0.06
    Act Density 0.124%

    No Known Activations