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

    Neuronpedia

    INDEX
    Explanations

    he or she speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    బడి
    0.34
    ဖွဲ့
    0.33
    かしい
    0.32
     Lists
    0.31
     codebase
    0.31
    Consider
    0.30
     Descriptions
    0.30
    ရှိ
    0.29
    Successful
    0.29
    смотрите
    0.29
    POSITIVE LOGITS
     said
    0.71
     exclaimed
    0.68
     murmured
    0.68
     whispered
    0.66
     mumbled
    0.61
     whisper
    0.60
     says
    0.59
     muttered
    0.59
    said
    0.57
    说道
    0.55
    Act Density 0.010%

    No Known Activations