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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of mechanical devices and systems

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

    usually or typically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.59
    SequentialGroup
    -0.58
     supernova
    -0.58
    potranspiration
    -0.55
    BibitemShut
    -0.54
     gracilis
    -0.54
    SplashScreen
    -0.54
     gneiss
    -0.54
    setCellValue
    -0.53
    lapsingToolbar
    -0.52
    POSITIVE LOGITS
     usually
    0.63
     zwykle
    0.52
     Usually
    0.52
     обычно
    0.51
     typically
    0.50
     généralement
    0.50
    usually
    0.49
     meestal
    0.49
     geralmente
    0.48
     biasanya
    0.47
    Act Density 0.256%

    No Known Activations