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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     document
    -1.22
     Document
    -1.03
    document
    -1.02
     myſelf
    -0.96
     themſelves
    -0.94
     himſelf
    -0.93
     Jefus
    -0.92
     purpoſe
    -0.91
    Document
    -0.91
    曖昧さ回避
    -0.88
    POSITIVE LOGITS
    webElement
    0.56
    stateProvider
    0.53
    ↵
    0.52
    ↵↵
    0.52
    n
    0.50
    ations
    0.49
     that
    0.49
    .
    0.49
     such
    0.48
     we
    0.48
    Act Density 1.248%

    No Known Activations