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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يول
    -0.09
     convencional
    -0.08
     Reve
    -0.08
     Weaver
    -0.08
    _Meta
    -0.08
     Born
    -0.08
    TMP
    -0.08
     Injectable
    -0.08
     Ingles
    -0.08
     Republike
    -0.08
    POSITIVE LOGITS
    特色
    0.13
     sightseeing
    0.11
     atrações
    0.09
     offerings
    0.09
    精彩
    0.09
     attractions
    0.09
     புக
    0.09
     amenities
    0.09
     scenic
    0.09
     бог
    0.08
    Act Density 0.020%

    No Known Activations