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

    Neuronpedia

    INDEX
    Explanations

    ego

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -1.35
    a
    -0.94
    ی
    -0.88
    sing
    -0.84
    e
    -0.83
    o
    -0.81
    sz
    -0.81
    sy
    -0.79
    sic
    -0.79
    sid
    -0.74
    POSITIVE LOGITS
     fédé
    0.60
     démocr
    0.57
     réfrig
    0.57
     découver
    0.56
     élect
    0.55
     européennes
    0.54
    CloseOperation
    0.54
     marquées
    0.53
     alimentaires
    0.53
     étrangères
    0.52
    Act Density 0.330%

    No Known Activations