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

    Neuronpedia

    INDEX
    Explanations

    structured data and code snippets

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

    Code or expressions including punctuation

    np_acts-logits-general · gemini-2.0-flash

    Tuple methods and closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.97
     and
    -0.86
     
    -0.85
     in
    -0.76
     a
    -0.68
     (
    -0.67
     of
    -0.66
     is
    -0.65
     i
    -0.64
     the
    -0.63
    POSITIVE LOGITS
     مشين
    1.30
    writeFieldEnd
    1.25
     CreateTagHelper
    1.24
     ProtoMessage
    1.19
     myſelf
    1.19
    twimg
    1.13
    GEBURTSDATUM
    1.13
     AssemblyCulture
    1.12
     Réponses
    1.12
    المناصب
    1.10
    Act Density 1.354%

    No Known Activations