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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "of" or "Support"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roveň
    0.53
     хоче
    0.46
     רק
    0.46
     अगदी
    0.44
    ಬ್ಬಿಣ
    0.44
     calcule
    0.43
     capire
    0.42
     inappropri
    0.42
     таких
    0.41
     genauso
    0.41
    POSITIVE LOGITS
     P
    0.58
     \|
    0.49
     B
    0.48
     D
    0.47
     II
    0.46
     Life
    0.46
     the
    0.46
     R
    0.45
     Medical
    0.45
     National
    0.44
    Act Density 0.155%

    No Known Activations