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

    Neuronpedia

    INDEX
    Explanations

    distinguishing between options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Và
    0.39
     ಹಾಗೂ
    0.36
     மற்றும்
    0.35
     असल्या
    0.35
     સહિત
    0.34
     Aufgrund
    0.34
     আৰু
    0.34
     आणि
    0.33
    ？”
    0.33
    और
    0.33
    POSITIVE LOGITS
    而是
    0.96
     बल्कि
    0.80
     بلکه
    0.77
    ;
    0.76
     sondern
    0.72
     hanem
    0.71
    ؛
    0.68
     sino
    0.66
     بلکہ
    0.66
    ；
    0.59
    Act Density 0.367%

    No Known Activations