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

    Neuronpedia

    INDEX
    Explanations

    hearing, seeing, enjoying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ใจ
    0.36
    魅
    0.36
    oea
    0.36
    情
    0.35
     Interested
    0.35
     ആക
    0.35
     되겠
    0.35
     berdasarkan
    0.34
     хотим
    0.34
     なお
    0.33
    POSITIVE LOGITS
     hearing
    0.89
    hearing
    0.75
    Hearing
    0.74
     seeing
    0.73
    有机会
    0.70
     Hearing
    0.67
     hear
    0.67
     being
    0.66
     watching
    0.64
    能够在
    0.64
    Act Density 0.012%

    No Known Activations