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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and subsequent words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    どのような
    0.95
     해당
    0.76
     bidirectional
    0.76
    人员
    0.75
    áles
    0.75
    の種類
    0.75
    当該
    0.73
     दर्शाता
    0.71
    琀
    0.70
    үндө
    0.70
    POSITIVE LOGITS
     clumsy
    0.97
     myself
    0.95
     smiled
    0.95
     grin
    0.94
     همیشه
    0.94
     weary
    0.94
     curls
    0.92
     Knows
    0.89
     suave
    0.89
     didn
    0.89
    Act Density 0.110%

    No Known Activations