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

    Neuronpedia

    INDEX
    Explanations

    code/technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snapped
    -0.07
     corporations
    -0.07
    construct
    -0.06
     validated
    -0.06
     pawn
    -0.06
    guild
    -0.06
     triumph
    -0.06
     Svg
    -0.06
    .Normal
    -0.06
     Dar
    -0.06
    POSITIVE LOGITS
    ives
    0.07
    ITIONAL
    0.07
    俊
    0.07
     aldığı
    0.07
    اذ
    0.07
    аними
    0.06
    雑
    0.06
    SIZE
    0.06
    --)↵
    0.06
    álie
    0.06
    Act Density 0.303%

    No Known Activations