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

    Neuronpedia

    INDEX
    Explanations

    brackets and index notations in code or data structures

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

    combining strings or arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ведь
    -0.31
    mittag
    -0.31
    ágok
    -0.30
    ID
    -0.30
    AppUser
    -0.29
    θρω
    -0.27
    إنه
    -0.27
     إنه
    -0.27
     routinely
    -0.27
     alone
    -0.26
    POSITIVE LOGITS
    ValueStyle
    0.70
    IsContent
    0.70
     ſein
    0.69
    multer
    0.69
    AndroidJUnit
    0.68
    mpagne
    0.66
    iſten
    0.65
     ſei
    0.65
     ſich
    0.63
    iſen
    0.62
    Act Density 0.003%

    No Known Activations