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

    Neuronpedia

    INDEX
    Explanations

    elaborate on any specific aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    任何
    0.86
     viable
    0.77
     vi
    0.75
    peut
    0.73
    every
    0.72
    োনা
    0.71
    ldigt
    0.71
    .$,
    0.71
    verständlich
    0.70
     conceivable
    0.70
    POSITIVE LOGITS
     of
    0.95
     của
    0.92
     specifiche
    0.90
    Particular
    0.87
     ของ
    0.87
     Particular
    0.87
     مختلفة
    0.86
     particular
    0.85
     particulares
    0.85
     perfetto
    0.84
    Act Density 0.017%

    No Known Activations