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

    Neuronpedia

    INDEX
    Explanations

    frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kol
    -0.08
     cartesian
    -0.07
    肖
    -0.07
     Castillo
    -0.07
    Ol
    -0.07
     Thomas
    -0.07
    Hon
    -0.07
     soll
    -0.07
     massive
    -0.07
    amon
    -0.07
    POSITIVE LOGITS
     frequency
    0.09
    allenge
    0.08
     Frequency
    0.08
    URITY
    0.08
     yytype
    0.07
    (freq
    0.07
     proficiency
    0.07
     موفق
    0.07
    (Encoding
    0.07
    URA
    0.07
    Act Density 0.014%

    No Known Activations