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

    Neuronpedia

    INDEX
    Explanations

    references to observations or claims made in a scientific context

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

    personal observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.39
    хьтан
    -0.35
    iyaki
    -0.35
     gemein
    -0.34
     esternos
    -0.33
    ionales
    -0.32
    ")[
    -0.31
    --*/
    -0.31
    foria
    -0.31
    filé
    -0.30
    POSITIVE LOGITS
     propOrder
    0.71
    SourceChecksum
    0.57
    (!__
    0.56
    ➋
    0.55
     '\\;'
    0.51
     disambiguazione
    0.50
    xnn
    0.50
    fillType
    0.50
     Corner
    0.47
    himself
    0.46
    Act Density 0.664%

    No Known Activations