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

    Neuronpedia

    INDEX
    Explanations

    connected to, capacity for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ៏
    0.53
     diput
    0.49
     आजा
    0.48
     skr
    0.45
     brokerage
    0.44
     bikin
    0.43
     hell
    0.43
     explosives
    0.43
     उ
    0.43
     compléter
    0.42
    POSITIVE LOGITS
    মাত্রা
    0.44
    কাজ
    0.42
    حال
    0.41
     Sufficient
    0.41
    藿
    0.41
    နှစ်
    0.40
    コーヒー
    0.40
     Poem
    0.39
    אי
    0.39
    hoppers
    0.38
    Act Density 0.000%

    No Known Activations