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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases indicating possibility

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

    modal verbs and auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Voll
    -0.36
    y
    -0.32
     your
    -0.31
        
    -0.31
     the
    -0.30
    『
    -0.30
     Schlaf
    -0.30
    –
    -0.30
                
    -0.29
     fulfillment
    -0.29
    POSITIVE LOGITS
    SequentialGroup
    0.96
    GEBURTSDATUM
    0.93
    تقاوى
    0.89
     للاسماء
    0.87
    AddTagHelper
    0.84
     للمعارف
    0.83
     الحره
    0.82
    argout
    0.80
    SharedDtor
    0.79
     EconPapers
    0.78
    Act Density 0.012%

    No Known Activations