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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CARD
    -0.07
    _ROLE
    -0.06
     PSG
    -0.06
    )./
    -0.06
    照片
    -0.06
    やる
    -0.06
    yor
    -0.06
    711
    -0.06
     compliments
    -0.06
    eygamber
    -0.06
    POSITIVE LOGITS
    affiliate
    0.07
    効
    0.06
     Fore
    0.06
    ILI
    0.06
    άλυ
    0.06
     آزمایش
    0.06
     zajímav
    0.06
     záp
    0.06
    .Map
    0.06
    ОН
    0.06
    Act Density 0.180%

    No Known Activations