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

    Neuronpedia

    INDEX
    Explanations

    technical terms and syntax related to programming, particularly in C or C-like languages

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

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kür
    -0.42
    Thick
    -0.38
    ajikan
    -0.35
     Thick
    -0.34
    andExpect
    -0.34
    whose
    -0.34
    reversed
    -0.33
    Ữ
    -0.32
    niña
    -0.32
    ürt
    -0.32
    POSITIVE LOGITS
    omock
    0.82
    __*/
    0.73
    avadoc
    0.68
    ArgsConstructor
    0.67
    printStackTrace
    0.66
    Captor
    0.65
    MLLoader
    0.62
    hyrchwyd
    0.60
    0.60
    createObject
    0.59
    Act Density 0.004%

    No Known Activations