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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    mathematical grouping symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.57
     éclairage
    -0.54
     bēr
    -0.53
    LookAnd
    -0.52
     lendemain
    -0.52
     området
    -0.52
     sukker
    -0.51
     étoient
    -0.51
    transQ
    -0.50
     acesta
    -0.50
    POSITIVE LOGITS
     Zacks
    0.43
    andExpect
    0.43
    TagMode
    0.43
     simp
    0.42
    awtextra
    0.42
     brist
    0.41
    )))),
    0.41
     boom
    0.41
     evolve
    0.40
     zing
    0.39
    Act Density 0.786%

    No Known Activations