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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     time
    0.47
     inhaling
    0.46
     acetyl
    0.46
     awaits
    0.46
     manipulate
    0.45
     average
    0.45
     consume
    0.45
     descre
    0.44
     helicopter
    0.43
     strawberries
    0.43
    POSITIVE LOGITS
    乂
    0.44
     MyApp
    0.44
    эд
    0.43
     Мы
    0.42
    MyApp
    0.42
     цей
    0.41
     MyApplication
    0.41
    Dal
    0.41
     стали
    0.41
     διά
    0.41
    Act Density 0.003%

    No Known Activations