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

    Neuronpedia

    INDEX
    Explanations

    phrases involving demonstrative pronouns and expressions of identity or existence

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

    French and Spanish "ce" and "lo"

    np_acts-logits-general · gemini-2.0-flash

    ce que

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.86
    SharedDtor
    -0.66
    PerformLayout
    -0.66
    consistent
    -0.60
     Medford
    -0.58
     Paglinawan
    -0.58
    Übersetzung
    -0.56
     Achtung
    -0.55
    complexContent
    -0.54
    entuh
    -0.54
    POSITIVE LOGITS
    !("{
    0.70
    \{\\
    0.62
    ;">
    0.61
    InteropServices
    0.60
     who
    0.59
    lossians
    0.58
     happening
    0.57
    THING
    0.55
    //{
    0.53
    guang
    0.52
    Act Density 0.057%

    No Known Activations