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

    Neuronpedia

    INDEX
    Explanations

    kill off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.59
    كي
    0.56
    בק
    0.55
    كان
    0.54
    ب
    0.53
    Ջ
    0.51
     zusätzlich
    0.51
    ಹೆ
    0.51
    אנ
    0.51
    بد
    0.50
    POSITIVE LOGITS
    </h1>
    0.55
     video
    0.47
    slip
    0.46
     are
    0.46
    =
    0.45
     n
    0.44
    -
    0.43
     slip
    0.42
     y
    0.42
    న్న
    0.41
    Act Density 0.000%

    No Known Activations