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

    Neuronpedia

    INDEX
    Explanations

    asking for confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    োদন
    0.47
     iterator
    0.45
     ቦታ
    0.45
     ഒഴി
    0.44
     epitaxial
    0.43
    ómago
    0.43
     რომ
    0.43
     voler
    0.43
    StringSet
    0.43
    际
    0.43
    POSITIVE LOGITS
    F
    0.67
    H
    0.58
    D
    0.57
    M
    0.55
    Fee
    0.54
    A
    0.54
    Bel
    0.52
    G
    0.52
    W
    0.52
    Apr
    0.51
    Act Density 0.002%

    No Known Activations