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

    Neuronpedia

    INDEX
    Explanations

    difficulty and purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্সের
    0.51
     benutzer
    0.50
    ویر
    0.47
    Setelah
    0.47
    聂
    0.47
    শনাল
    0.45
    muslim
    0.45
     tipe
    0.45
     avulla
    0.44
     cardiomyocyte
    0.44
    POSITIVE LOGITS
    9
    0.47
     трудно
    0.46
    difficult
    0.45
    6
    0.45
     difficult
    0.45
    7
    0.44
     khó
    0.43
    各種
    0.43
     отече
    0.43
    4
    0.41
    Act Density 0.005%

    No Known Activations