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

    Neuronpedia

    INDEX
    Explanations

    Promise.all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大
    0.65
    t
    0.58
    他的
    0.55
     он
    0.55
    c
    0.55
    tu
    0.54
    他
    0.54
    其他
    0.53
    我
    0.53
     इस्लामिक
    0.52
    POSITIVE LOGITS
     Have
    0.54
     Does
    0.51
    icent
    0.51
    isLen
    0.50
    èt
    0.48
    <
    0.48
     Remembrance
    0.48
     Make
    0.47
    isan
    0.47
    <0xBF>
    0.47
    Act Density 0.000%

    No Known Activations