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

    Neuronpedia

    INDEX
    Explanations

    conditional and contrasting phrases

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

    introduces a contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SerializeField
    -0.35
     every
    -0.32
    beforeSend
    -0.31
     Great
    -0.31
     GREAT
    -0.30
     par
    -0.30
     Paglinawan
    -0.30
    Great
    -0.29
     Par
    -0.29
     the
    -0.29
    POSITIVE LOGITS
    ⟬
    0.71
    TypedDataSet
    0.68
     nakalista
    0.64
    addContainerGap
    0.63
     betweenstory
    0.60
    UIControlState
    0.59
     Wikimedijinoj
    0.57
    CppMethod
    0.57
    extAlignment
    0.57
    ChildScrollView
    0.57
    Act Density 0.133%

    No Known Activations