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

    Neuronpedia

    INDEX
    Explanations

    Improved lung function tests

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical or hexadecimal color values in programming and markup code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    姿
    -0.83
    Idade
    -0.79
    靡
    -0.78
    ność
    -0.76
    angkap
    -0.75
    blocking
    -0.75
    딱
    -0.74
    butyl
    -0.73
    swept
    -0.72
    setOpaque
    -0.72
    POSITIVE LOGITS
    Changing
    0.88
    Bytes
    0.81
    Zwischen
    0.77
    EMS
    0.76
    orkshire
    0.75
     chiara
    0.75
    pentine
    0.75
     Contribu
    0.75
    ững
    0.75
     Examples
    0.74
    Act Density 0.000%

    No Known Activations