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

    Neuronpedia

    INDEX
    Explanations

    technical terms or commands related to programming or data handling

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

    Code, commands, and definitions

    np_acts-logits-general · gemini-2.0-flash

    show command identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dafx
    -0.70
     ModelExpression
    -0.68
    MLLoader
    -0.63
     doInBackground
    -0.61
    jän
    -0.60
    وارض
    -0.58
    CppCodeGen
    -0.56
     fVar
    -0.55
    psack
    -0.54
     Italijani
    -0.54
    POSITIVE LOGITS
    MemoryWarning
    0.61
     lenker
    0.59
     palo
    0.56
    XmlAccessorType
    0.55
     يتيمه
    0.54
    juni
    0.52
     समीक्षाएं
    0.51
    iena
    0.50
    yang
    0.48
    sal
    0.48
    Act Density 0.303%

    No Known Activations