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

    Neuronpedia

    INDEX
    Explanations

    5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    via
    0.83
    醫
    0.78
    fahren
    0.77
    嗳
    0.74
    giving
    0.73
    tw
    0.73
     Batik
    0.73
    녜
    0.73
    chen
    0.72
    vars
    0.72
    POSITIVE LOGITS
     acyl
    0.80
     Bolsonaro
    0.78
     Están
    0.77
     ruffle
    0.75
    irittura
    0.75
     Dirac
    0.72
     racket
    0.71
     complication
    0.71
     laminar
    0.71
     meniscus
    0.71
    Act Density 0.003%

    No Known Activations