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

    Neuronpedia

    INDEX
    Explanations

    dates and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ó
    0.70
     ciò
    0.63
    д
    0.62
     bruke
    0.60
     ĝi
    0.60
    դ
    0.58
    你
    0.57
     velocidad
    0.57
    ându
    0.57
     măsur
    0.57
    POSITIVE LOGITS
     the
    0.88
     in
    0.71
    the
    0.70
     of
    0.59
     at
    0.58
     conifers
    0.57
     an
    0.56
     reorganized
    0.55
     a
    0.55
    r
    0.54
    Act Density 0.078%

    No Known Activations