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

    Neuronpedia

    INDEX
    Explanations

    continuous or repetition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weekly
    0.39
    વાહી
    0.38
     ATTOR
    0.38
     \%,
    0.38
     Yearly
    0.37
    算
    0.37
     annually
    0.37
     Отече
    0.36
    meth
    0.36
    ুকের
    0.35
    POSITIVE LOGITS
     continuous
    0.57
     Continuous
    0.57
    Continuous
    0.55
     kontinuier
    0.55
     सतत
    0.54
    continuous
    0.53
     mid
    0.53
     continuo
    0.50
     وسط
    0.50
     kontin
    0.48
    Act Density 0.000%

    No Known Activations