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

    Neuronpedia

    INDEX
    Explanations

    reportedly drafted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sometimes
    0.49
     sometimes
    0.48
     kadang
    0.47
     parfois
    0.45
     manchmal
    0.44
     บาง
    0.43
     quelquefois
    0.42
     oftentimes
    0.42
    Occasionally
    0.42
    一定的
    0.41
    POSITIVE LOGITS
     according
    0.54
     According
    0.54
    据悉
    0.54
    according
    0.47
     दिलचस्प
    0.44
     Unable
    0.44
     según
    0.44
     Acting
    0.44
     Launched
    0.43
     Fitting
    0.43
    Act Density 0.007%

    No Known Activations