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

    Neuronpedia

    INDEX
    Explanations

    instances of end-of-turn signals in a conversation model or dialogue structure

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

    code and non-english terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.53
     puro
    -0.38
     newItem
    -0.36
     批
    -0.35
    GUEST
    -0.35
    庁
    -0.34
     Stokes
    -0.34
    yarnpkg
    -0.34
     Münch
    -0.33
    serialization
    -0.33
    POSITIVE LOGITS
    новништво
    0.61
    0.56
     للاسماء
    0.55
    rungsseite
    0.54
     HasFactory
    0.53
    ⤒
    0.48
    Personendaten
    0.48
     мәкал
    0.48
    ("")]
    0.47
    Jereo
    0.47
    Act Density 0.215%

    No Known Activations