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

    Neuronpedia

    INDEX
    Explanations

    aether and its derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ie
    0.69
    ru
    0.68
    ra
    0.63
    ib
    0.62
     was
    0.59
    ien
    0.57
     ប
    0.56
    b
    0.56
     be
    0.56
     cria
    0.55
    POSITIVE LOGITS
    ل
    0.67
    л
    0.63
    ט
    0.60
    лийн
    0.57
    טו
    0.56
    력
    0.55
     ateliers
    0.55
    ITAL
    0.54
    тод
    0.54
    ುತ್ತಾರೆ
    0.53
    Act Density 0.000%

    No Known Activations