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

    Neuronpedia

    INDEX
    Explanations

    parts of names, especially the suffixes "chen," "nten," "erin," "ishi," and "aran."

    oai_token-act-pair · gemini-2.0-flash

    tokens containing 'aran' or related variants

    np_token-act-pair-logits · gpt-4o-mini

    proper nouns in research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esternos
    -0.49
     unknownFields
    -0.49
    oneg
    -0.48
    >//
    -0.46
    Rüyada
    -0.45
     law
    -0.44
     VIAF
    -0.44
    <bos>
    -0.42
    ommen
    -0.42
    SQLException
    -0.41
    POSITIVE LOGITS
    hões
    0.60
    SharedCtor
    0.59
     تضيفلها
    0.58
    FTFY
    0.56
    UrlResolution
    0.55
    Tembelea
    0.55
    IsMutable
    0.54
    himp
    0.54
    下载附件
    0.53
    providedIn
    0.52
    Act Density 0.459%

    No Known Activations