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

    Neuronpedia

    INDEX
    Explanations

    dollar signs representing equations and the word 'import'

    oai_token-act-pair · gemini-2.0-flash

    code and math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numberOfRows
    -0.48
    Listener
    -0.47
    kotlin
    -0.46
     hard
    -0.45
    Bitpie
    -0.45
    gua
    -0.44
    ulers
    -0.44
    gerufen
    -0.43
    FileOutputStream
    -0.43
    vium
    -0.43
    POSITIVE LOGITS
     otomatig
    0.87
    Autoritní
    0.84
    bewerken
    0.78
     surla
    0.78
    NameInMap
    0.78
    IUrlHelper
    0.77
     Administrativna
    0.75
     Wikimedijinoj
    0.71
     nahilalakip
    0.70
     oprot
    0.68
    Act Density 1.555%

    No Known Activations