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

    Neuronpedia

    INDEX
    Explanations

    references to religious authority and doctrine

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

    Follows "great," "full," or "er."

    np_acts-logits-general · gemini-2.0-flash

    common words followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Conserv
    -0.50
    期刊论文
    -0.49
    Personendaten
    -0.45
    ereich
    -0.44
     Conserv
    -0.44
    Personensuche
    -0.42
     pedals
    -0.42
    capai
    -0.41
     console
    -0.41
    oğlu
    -0.41
    POSITIVE LOGITS
    WireFormatLite
    0.49
    ftagPool
    0.40
    mobileqq
    0.38
    Kjelder
    0.37
     Arn
    0.36
     فريبيس
    0.36
     disciplina
    0.35
    Arn
    0.35
    Sharper
    0.35
     Stir
    0.34
    Act Density 0.044%

    No Known Activations