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

    Neuronpedia

    INDEX
    Explanations

    syntactic tokens and structural components in programming or mathematical expressions

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

    bounding boxes coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.50
     Schmid
    -0.44
     Pfe
    -0.44
     mixed
    -0.42
    crí
    -0.42
     dita
    -0.42
    colgante
    -0.42
     observación
    -0.41
     Rys
    -0.41
     Lampe
    -0.41
    POSITIVE LOGITS
     defaultstate
    0.51
    saraba
    0.49
    Personendaten
    0.47
     mergeFrom
    0.46
    windowFixed
    0.45
     QtCore
    0.43
    addPreferredGap
    0.43
    endpush
    0.40
    Diwedd
    0.39
     CreateTagHelper
    0.39
    Act Density 0.005%

    No Known Activations