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

    Neuronpedia

    INDEX
    Explanations

    seized him, pulled my

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     많이
    1.29
    めっちゃ
    1.26
     bzw
    1.17
     dużo
    1.17
     IMHO
    1.16
    တဲ့
    1.10
    📈
    1.09
     attualmente
    1.09
     상당히
    1.07
     굉장히
    1.06
    POSITIVE LOGITS
     imposs
    0.94
     his
    0.93
     instinctively
    0.92
     trembling
    0.90
     wretched
    0.86
     dusk
    0.84
     aching
    0.83
     every
    0.82
     nervously
    0.82
     whispered
    0.82
    Act Density 0.297%

    No Known Activations