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

    Neuronpedia

    INDEX
    Explanations

    URL routing or updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Choisissez
    0.49
    Rüyada
    0.46
    剰
    0.46
    ordine
    0.45
    riol
    0.44
    ri
    0.44
    Ordinate
    0.44
    Não
    0.43
     connot
    0.42
    ières
    0.42
    POSITIVE LOGITS
     bych
    0.46
     एक
    0.43
     सराह
    0.42
     penet
    0.41
     živ
    0.41
     بشكل
    0.40
     Sanford
    0.40
    ដូច្ន
    0.38
     Cree
    0.38
     достаточно
    0.38
    Act Density 0.003%

    No Known Activations