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

    Neuronpedia

    INDEX
    Explanations

    structured data or coding syntax related to templates or variables

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

    code and markup elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.46
    EDEFAULT
    -0.44
     GenerationType
    -0.42
    发表于
    -0.40
    iastes
    -0.39
    makeText
    -0.38
    lawayo
    -0.36
     Oph
    -0.36
    recently
    -0.35
    flashdata
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.56
    OGND
    0.50
     propOrder
    0.47
    enumii
    0.46
    Autoritní
    0.45
     معن
    0.45
    TokenName
    0.45
    idée
    0.44
     itſelf
    0.44
    FunctionFlags
    0.44
    Act Density 0.000%

    No Known Activations