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

    Neuronpedia

    INDEX
    Explanations

    interpolation method is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orifices
    0.22
     of
    0.22
    GoObject
    0.22
     gleichen
    0.22
     drows
    0.21
     ஒன்றை
    0.21
     Strecke
    0.21
     scrotum
    0.21
     solcher
    0.21
    文字列
    0.20
    POSITIVE LOGITS
    의
    0.33
    的
    0.32
     adlı
    0.32
     has
    0.31
    ⁩
    0.31
     is
    0.29
    ની
    0.29
     的
    0.28
    作为
    0.28
    에
    0.28
    Act Density 2.714%

    No Known Activations