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

    Neuronpedia

    INDEX
    Explanations

    integration with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    謾
    0.34
     მიმო
    0.33
    kd
    0.32
    鱿
    0.31
     punctatis
    0.29
    ról
    0.29
    kde
    0.29
    uramente
    0.29
     thereon
    0.29
    संस्करण
    0.28
    POSITIVE LOGITS
    กับ
    1.52
     עם
    1.29
     với
    1.25
     with
    1.24
     dengan
    1.17
     avec
    1.16
    กับการ
    1.10
    ກັບ
    1.00
    with
    0.97
     kanssa
    0.94
    Act Density 0.081%

    No Known Activations