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

    Neuronpedia

    INDEX
    Explanations

    keeping like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.07
    electrical
    1.04
    children
    0.98
    class
    0.94
     Church
    0.94
    elementary
    0.93
     タイヤ
    0.92
    stein
    0.92
    3
    0.90
     περίπτωση
    0.89
    POSITIVE LOGITS
    ⤠
    1.14
     الت
    1.13
     تت
    1.12
     viss
    1.12
     يت
    1.11
     delve
    1.10
    <0x1E>
    1.09
     وق
    1.08
     ك
    1.08
     boost
    1.06
    Act Density 0.000%

    No Known Activations