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

    Neuronpedia

    INDEX
    Explanations

    how do you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.91
    在
    0.77
     in
    0.76
     inorder
    0.61
    a
    0.60
     universit
    0.59
     presenceData
    0.58
     ogran
    0.58
    不允许
    0.56
     inget
    0.56
    POSITIVE LOGITS
    adayo
    0.65
    oles
    0.61
     Konrad
    0.61
    ü
    0.61
    кова
    0.60
     Koenig
    0.57
    ев
    0.57
    ة
    0.57
    ijske
    0.56
    isches
    0.55
    Act Density 0.001%

    No Known Activations