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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentences that convey uncertainty or questions

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

    Followed by questions or pronouns

    np_acts-logits-general · gemini-2.0-flash

    demonstrative or possessive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.80
    tagHelperRunner
    -0.76
    NameInMap
    -0.75
     AssemblyTitle
    -0.71
    __(/*!
    -0.65
    ReusableCell
    -0.61
    TargetException
    -0.59
     Wikimedijinoj
    -0.59
     <<<<<<<<<<<<<<
    -0.59
    GIVEREF
    -0.59
    POSITIVE LOGITS
    这个
    0.52
    這個
    0.51
    こいつ
    0.50
     dessen
    0.49
     whose
    0.49
     Celui
    0.47
     éste
    0.47
     deze
    0.45
     这个
    0.44
     this
    0.44
    Act Density 0.711%

    No Known Activations