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

    Neuronpedia

    INDEX
    Explanations

    punctuation or symbols that denote the end of sentences or significant pauses in text

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

    new sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.49
    Numerade
    -0.48
    Życiorys
    -0.46
    つつ
    -0.42
    IntOverflow
    -0.40
     gewisse
    -0.40
    ̯
    -0.40
    RegistryLite
    -0.40
    像是
    -0.38
     SwiftUI
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    0.55
    tanleria
    0.53
     '{@
    0.46
    abases
    0.44
     ſy
    0.43
    ulongan
    0.43
     faſt
    0.43
     ingrediente
    0.41
     alarme
    0.41
     HFILL
    0.41
    Act Density 0.157%

    No Known Activations