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

    Neuronpedia

    INDEX
    Explanations

    phrases and contexts that emphasize detailed descriptions or explanations

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

    in detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    colgante
    -0.48
    rungsseite
    -0.47
     opgenomen
    -0.46
    aarrggbb
    -0.43
    UrlResolution
    -0.42
     wijze
    -0.42
    pantalón
    -0.41
     vuestros
    -0.40
    ""}
    -0.39
     ricordare
    -0.38
    POSITIVE LOGITS
    HandlerContext
    0.44
    NOPQRST
    0.42
    ariConfig
    0.41
     dyna
    0.41
    ありがとうございました
    0.40
    SPATH
    0.40
    copic
    0.40
    :+:
    0.40
    Rüyada
    0.39
    batim
    0.39
    Act Density 0.046%

    No Known Activations