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

    Neuronpedia

    INDEX
    Explanations

    Fuzzy Logic Interface Unified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hoea
    2.09
     النهارده
    2.08
     gelungen
    1.99
    Didn
    1.98
     sebab
    1.97
     Tipp
    1.95
     ofta
    1.91
    didn
    1.89
     geweest
    1.86
     favorita
    1.86
    POSITIVE LOGITS
    8
    1.96
    6
    1.93
    7
    1.93
     lastly
    1.81
    rinsic
    1.75
    mehr
    1.70
     fizik
    1.68
     Corpo
    1.67
    adays
    1.66
     immerse
    1.65
    Act Density 0.199%

    No Known Activations