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

    Neuronpedia

    INDEX
    Explanations

    financial tax liability and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     அல்லது
    0.59
     hoặc
    0.56
     veya
    0.53
     ponieważ
    0.51
     một
    0.50
     અથવા
    0.50
     proiz
    0.49
     dört
    0.49
    anlı
    0.49
     glLight
    0.48
    POSITIVE LOGITS
    占比
    0.66
     uptick
    0.66
     realizzazione
    0.65
    скім
    0.64
     downsides
    0.61
    ੁ
    0.61
    gets
    0.59
     少し
    0.59
    後的
    0.58
     realizzare
    0.58
    Act Density 0.022%

    No Known Activations