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

    Neuronpedia

    INDEX
    Explanations

    abstract qualities after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Those
    0.37
     generates
    0.36
     Those
    0.35
     最
    0.34
     gets
    0.34
    There
    0.33
    最有
    0.33
     সবচেয়ে
    0.33
     heeft
    0.32
     sogen
    0.32
    POSITIVE LOGITS
     fact
    0.81
     importance
    0.80
     Tatsache
    0.74
     lack
    0.72
     faptul
    0.71
     absurdity
    0.70
    importance
    0.69
     inability
    0.68
     prevalence
    0.67
     impossibility
    0.66
    Act Density 0.040%

    No Known Activations