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

    Neuronpedia

    INDEX
    Explanations

    phrases related to licensing and usage terms, specifically in a software context

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

    "AS IS" disclaimer in legal contexts

    np_acts-logits-general · gemini-2.0-flash

    as is disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.06
    IntoConstraints
    -0.88
    出版年
    -0.88
    AddTagHelper
    -0.87
    +#+#
    -0.87
     disambiguazione
    -0.85
     myſelf
    -0.84
     Houſe
    -0.84
     MainAxisSize
    -0.83
     препратки
    -0.83
    POSITIVE LOGITS
    '
    0.68
    ,
    0.67
    <bos>
    0.65
    ’
    0.63
     he
    0.61
     and
    0.60
    -
    0.56
     in
    0.56
     
    0.56
     also
    0.56
    Act Density 0.006%

    No Known Activations