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

    Neuronpedia

    INDEX
    Explanations

    code snippets that do addition or subtraction

    oai_token-act-pair · gemini-2.0-flash

    +=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     архивлан
    -0.61
     Extragalactic
    -0.56
    IUrlHelper
    -0.55
     incomplète
    -0.54
    :✨
    -0.51
    Descripció
    -0.50
    MigrationBuilder
    -0.50
     MenuView
    -0.49
    writeField
    -0.49
    igshid
    -0.49
    POSITIVE LOGITS
    <bos>
    0.79
    Hentet
    0.50
     kalah
    0.49
    VELAND
    0.48
     communiquer
    0.47
     فريبيس
    0.45
    CGRectMake
    0.44
     ✭✭
    0.44
    atric
    0.44
    idad
    0.43
    Act Density 5.478%

    No Known Activations