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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming keywords and syntax

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

    starting examples or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.68
     queſta
    -0.66
     للمعارف
    -0.66
    offsetof
    -0.62
    parsedMessage
    -0.62
    TagMode
    -0.61
     ſind
    -0.60
     &___
    -0.58
    Datuak
    -0.56
     ſei
    -0.56
    POSITIVE LOGITS
     HasFactory
    0.42
     idéia
    0.37
     razonable
    0.36
    Isso
    0.35
     inspiração
    0.35
     limpio
    0.32
    omitempty
    0.32
     Against
    0.32
     oculto
    0.31
     일
    0.31
    Act Density 0.085%

    No Known Activations