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

    Neuronpedia

    INDEX
    Explanations

    references to handwritten and typed documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    typing, handwriting, printing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umoj
    -0.37
    räck
    -0.36
     navideña
    -0.36
     aldea
    -0.34
     empirical
    -0.34
    積
    -0.34
    ración
    -0.34
     estrategia
    -0.33
    empi
    -0.32
     bocca
    -0.32
    POSITIVE LOGITS
    Tikang
    0.74
    rungsseite
    0.66
     resourceCulture
    0.56
     faſt
    0.52
     typewriter
    0.48
     handwriting
    0.47
     Typing
    0.46
    SourceChecksum
    0.46
     printing
    0.45
    rawDesc
    0.43
    Act Density 0.126%

    No Known Activations