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

    Neuronpedia

    INDEX
    Explanations

    slightly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     !(
    0.41
    thebetter
    0.39
     ICE
    0.39
     {{\
    0.39
     banyak
    0.38
     glTexParameteri
    0.38
    !
    0.38
     Neust
    0.38
    schild
    0.38
     ITER
    0.37
    POSITIVE LOGITS
     mildly
    0.53
    而已
    0.52
     tweak
    0.48
    y
    0.48
     glimpse
    0.47
     tweaks
    0.47
     chút
    0.44
    쿵
    0.43
     약간
    0.43
    程度
    0.42
    Act Density 0.334%

    No Known Activations