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

    Neuronpedia

    INDEX
    Explanations

    slide content summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atial
    0.49
    ifty
    0.48
     automóviles
    0.43
     Defts
    0.43
     thats
    0.42
    llium
    0.42
    라우
    0.42
     clientes
    0.42
    ****/
    0.42
    प्रधान
    0.41
    POSITIVE LOGITS
     Stroke
    0.46
    \
    0.45
    ovu
    0.44
     ست
    0.44
    描述
    0.43
    υ
    0.43
     Calendar
    0.42
     ለ
    0.42
    Stroke
    0.42
     COLL
    0.42
    Act Density 0.003%

    No Known Activations