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

    Neuronpedia

    INDEX
    Explanations

    specific boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    修订
    0.40
    itemList
    0.39
    ItemId
    0.39
    會員
    0.39
    chk
    0.39
    นน
    0.39
    ivale
    0.38
    ולי
    0.38
    ទៀ
    0.38
     inaccuracy
    0.38
    POSITIVE LOGITS
     Structure
    0.46
     Occasionally
    0.45
     occasionally
    0.44
     reminiscent
    0.43
     Strukturen
    0.41
     geg
    0.38
     Recognition
    0.38
     Hazards
    0.37
    器
    0.37
     gekommen
    0.37
    Act Density 0.001%

    No Known Activations