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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    坳
    0.44
     costruito
    0.42
     impresion
    0.41
     impressed
    0.40
     perovsk
    0.40
    对应的
    0.40
     frequencies
    0.38
     improvised
    0.38
     العاش
    0.38
    爱
    0.38
    POSITIVE LOGITS
     hưởng
    0.45
     đó
    0.45
     tìm
    0.41
     lối
    0.40
     bội
    0.40
     Tìm
    0.39
    Tìm
    0.39
     nhảy
    0.39
    Ư
    0.39
    PayPal
    0.39
    Act Density 0.000%

    No Known Activations