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

    Neuronpedia

    INDEX
    Explanations

    This invention relates to

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

    code-related elements such as JavaScript, HTML tags, and programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    cessive
    -0.75
    لاس
    -0.74
     لم
    -0.73
     Gloss
    -0.71
     dzī
    -0.70
    ⋮
    -0.70
    拍
    -0.70
    illegal
    -0.70
     excessive
    -0.69
    zessin
    -0.69
    POSITIVE LOGITS
    TERM
    0.82
    sze
    0.81
     konsumen
    0.79
    ucun
    0.76
     papaya
    0.75
     musculoskeletal
    0.75
    mus
    0.75
    𝕍
    0.75
     héroes
    0.74
    IDI
    0.74
    Act Density 0.011%

    No Known Activations