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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and measurements related to products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    characteristics, types, styles, genres, features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.36
    mites
    -0.34
     ſmall
    -0.34
     fordern
    -0.33
    Vod
    -0.33
    tempted
    -0.33
    HHHHHHHH
    -0.32
    皱眉
    -0.32
     createSprite
    -0.31
    maka
    -0.31
    POSITIVE LOGITS
     style
    0.68
     Style
    0.60
     type
    0.59
    ลักษ
    0.59
     features
    0.57
    特徴
    0.57
     mode
    0.56
     genre
    0.54
     estilo
    0.54
    Style
    0.53
    Act Density 0.014%

    No Known Activations