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

    Neuronpedia

    INDEX
    Explanations

    categorized by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    י
    0.46
    蚛
    0.45
     dwRes
    0.43
     Архів
    0.43
     מר
    0.43
     சம்பவ
    0.43
     דר
    0.43
    preliquidacion
    0.42
     profund
    0.42
     التن
    0.42
    POSITIVE LOGITS
    CK
    0.45
     speaking
    0.41
     leuke
    0.39
     barely
    0.39
     bunch
    0.38
    ogie
    0.38
    uance
    0.37
    Mik
    0.37
     Duk
    0.37
     Mick
    0.37
    Act Density 0.139%

    No Known Activations