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

    Neuronpedia

    INDEX
    Explanations

    references to models and their associated parameters in a machine learning context

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

    machine learning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arraycopy
    -0.41
     tĩnh
    -0.39
    append
    -0.38
     lots
    -0.38
     yellow
    -0.36
     tatuagens
    -0.36
    :+:
    -0.36
    malloc
    -0.35
     white
    -0.35
    เติม
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    0.65
    FormTagHelper
    0.56
     Ideology
    0.54
    évaluateur
    0.48
     CURIAM
    0.48
     Regiment
    0.47
    nologi
    0.47
    TagMode
    0.46
    fez
    0.46
     insurer
    0.46
    Act Density 0.037%

    No Known Activations