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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     없음
    -0.07
     seçim
    -0.07
     سرعت
    -0.06
     DOT
    -0.06
    (n
    -0.06
    เปอร
    -0.06
    曰
    -0.06
     StringType
    -0.06
    472
    -0.06
     кирп
    -0.06
    POSITIVE LOGITS
     Guards
    0.07
     Craft
    0.07
     полос
    0.06
    culo
    0.06
     Qaeda
    0.06
    _".$
    0.06
    DWORD
    0.06
    �
    0.06
    career
    0.06
    cur
    0.06
    Act Density 0.001%

    No Known Activations