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

    Neuronpedia

    INDEX
    Explanations

    pericard, coccus, carpets, Magnetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.95
    ल
    0.62
    л
    0.62
     whak
    0.61
    ре
    0.60
    arrêt
    0.60
     νέ
    0.59
    ंदे
    0.59
    வைகள்
    0.58
     pâle
    0.58
    POSITIVE LOGITS
    。
    0.86
    ↵
    0.65
    ；
    0.65
     on
    0.64
    ।
    0.61
     with
    0.57
    IO
    0.57
     by
    0.56
    B
    0.56
     in
    0.54
    Act Density 0.000%

    No Known Activations