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

    Neuronpedia

    INDEX
    Explanations

    sections of text labeled as descriptions or product descriptions

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

    description headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πάν
    -0.35
     unaweza
    -0.31
    BeanFactory
    -0.29
    throwaway
    -0.28
    czyn
    -0.28
    foregroundColor
    -0.28
    kait
    -0.27
    astéroïdes
    -0.26
    uguetes
    -0.26
    ungere
    -0.26
    POSITIVE LOGITS
     DESCRIPTION
    0.73
    iettivo
    0.71
    出版年
    0.66
     description
    0.64
     Paglinawan
    0.63
    RTGC
    0.61
    ErrUnexpectedEOF
    0.61
    DESCRIPTION
    0.60
    Опис
    0.60
     Description
    0.60
    Act Density 0.116%

    No Known Activations