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

    Neuronpedia

    INDEX
    Explanations

    code snippets from C# and javascript

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.88
     houſe
    -0.78
     Houſe
    -0.73
     purpoſe
    -0.71
     myſelf
    -0.68
     Monfieur
    -0.66
     itſelf
    -0.65
     leſs
    -0.64
     leaſt
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
    SharedDtor
    1.05
    abestanden
    0.93
     EconPapers
    0.78
    rungsseite
    0.76
    XmlAccessorType
    0.69
    ponses
    0.68
    GOTREF
    0.68
    Rüyada
    0.67
    InstanceState
    0.66
    TemporalType
    0.65
    Act Density 1.417%

    No Known Activations