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

    Neuronpedia

    INDEX
    Explanations

    conversational replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     موارد
    0.33
    PDF
    0.29
     عناصر
    0.29
     resource
    0.28
     document
    0.27
    Resource
    0.27
     refract
    0.27
     turnkey
    0.26
    TAINS
    0.26
    வதற்கான
    0.26
    POSITIVE LOGITS
     replied
    0.45
     replying
    0.42
     reply
    0.38
     hermano
    0.35
     replies
    0.34
     exclaimed
    0.34
     angrily
    0.34
     antwort
    0.33
     jesus
    0.32
     fratello
    0.32
    Act Density 0.046%

    No Known Activations