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

    Neuronpedia

    INDEX
    Explanations

    words indicating the existence of things

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OFDb
    -0.65
    "):
    -0.61
    ")){
    -0.60
    "){
    -0.60
    "]="
    -0.60
     ')[
    -0.57
    $")
    -0.57
    TypedDataSet
    -0.56
     שלנו
    -0.54
    pozdrawiam
    -0.54
    POSITIVE LOGITS
    oplasma
    0.58
    rometry
    0.52
    Traducción
    0.51
    앵
    0.51
    AnimationFrame
    0.48
    баты
    0.48
    tals
    0.47
    rungsseite
    0.46
    invokeLater
    0.46
     nsw
    0.46
    Act Density 2.025%

    No Known Activations