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

    Neuronpedia

    INDEX
    Explanations

    lack of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ώστε
    3.05
    pushButton
    3.00
     hashMap
    2.87
     runaway
    2.72
    jší
    2.68
    numericUpDown
    2.66
     मजबूर
    2.61
     toBe
    2.59
     Lizzie
    2.57
    ductory
    2.54
    POSITIVE LOGITS
    ا
    3.05
    as
    2.74
    ت
    2.59
    at
    2.57
     Faites
    2.50
     escrit
    2.43
    Salut
    2.42
    ı
    2.40
    বের
    2.40
    in
    2.35
    Act Density 0.037%

    No Known Activations