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

    Neuronpedia

    INDEX
    Explanations

    words ending in "lies", "cast" or "ny" as well as the phrase "doubling down"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prepareStatement
    -0.48
     hæ
    -0.48
     запас
    -0.48
    parseColor
    -0.48
    Enquiries
    -0.47
    rophilic
    -0.47
    NewUrlParser
    -0.47
    Carriera
    -0.46
    iol
    -0.46
     lancar
    -0.46
    POSITIVE LOGITS
    
    0.81
    MemoryWarning
    0.71
    NameInMap
    0.69
    Datuak
    0.67
     viewDidLoad
    0.67
    <bos>
    0.65
     <=",
    0.63
    évaluateur
    0.61
     insuffisamment
    0.61
    principalTable
    0.61
    Act Density 1.143%

    No Known Activations