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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or conditions

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

    Tokens that start new sentences

    np_acts-logits-general · gemini-2.0-flash

    discourse markers, conjunctions, and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.57
     newOwner
    -0.56
     ErrInvalid
    -0.56
    WebElementEntity
    -0.56
     oprot
    -0.53
    oredCriteria
    -0.52
    RectangleBorder
    -0.52
    tisseur
    -0.51
    enterOuterAlt
    -0.50
    kháu
    -0.50
    POSITIVE LOGITS
     many
    0.40
    不少
    0.38
     Czy
    0.38
     social
    0.38
     seeming
    0.37
    ไ
    0.36
    Println
    0.35
     why
    0.35
    many
    0.34
    kah
    0.34
    Act Density 0.958%

    No Known Activations