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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worst
    -0.07
    hog
    -0.07
    .first
    -0.07
    Infrastructure
    -0.07
    -two
    -0.07
    覺
    -0.06
    ЕН
    -0.06
    258
    -0.06
    wendung
    -0.06
    -State
    -0.06
    POSITIVE LOGITS
     기본
    0.06
     uživatel
    0.06
     γλώ
    0.06
     asiat
    0.06
     ممن
    0.06
    .strictEqual
    0.06
    Freq
    0.06
     reconnect
    0.05
     roman
    0.05
     equ
    0.05
    Act Density 0.310%

    No Known Activations