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

    Neuronpedia

    INDEX
    Explanations

    symbols, particularly those used in programming or licensing contexts

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

    special character prefixes for code/commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.56
     CreateTagHelper
    -0.53
    ltä
    -0.41
    Menurutnya
    -0.41
     चीज़ों
    -0.41
     enfermed
    -0.39
     JpaRepository
    -0.39
     avoient
    -0.39
     jonka
    -0.38
    튿
    -0.38
    POSITIVE LOGITS
    └──
    0.68
    ├──
    0.65
     disambiguazione
    0.52
    ✑
    0.47
     verti
    0.45
    homonymie
    0.45
    ⓘ
    0.44
    └
    0.44
     ujednoznacz
    0.44
     ואת
    0.43
    Act Density 0.121%

    No Known Activations