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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to expressions or examples

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

    "ex" prefix

    np_acts-logits-general · gemini-2.0-flash

    words starting with ex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setViewportView
    -0.84
    sidemargin
    -0.73
    Referències
    -0.69
    didSet
    -0.69
    ReferenceEquals
    -0.66
     keyPressed
    -0.65
    LabelTagHelper
    -0.65
     AppBar
    -0.64
    IsContent
    -0.63
    epoca
    -0.62
    POSITIVE LOGITS
     ex
    1.09
     Ex
    1.07
    Ex
    1.00
     EX
    0.97
    ex
    0.93
    EX
    0.83
     exc
    0.69
     exp
    0.69
    외
    0.60
     ек
    0.59
    Act Density 0.082%

    No Known Activations