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

    Neuronpedia

    INDEX
    Explanations

    knowledge cutoff: year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    崦
    0.82
    বিশিষ্ট
    0.81
    CheckingType
    0.78
    に行って
    0.76
    ائص
    0.75
    訸
    0.73
    actionBarTab
    0.73
    expressing
    0.72
    䚺
    0.71
    㴓
    0.71
    POSITIVE LOGITS
    2
    1.05
    4
    0.94
    6
    0.93
    1
    0.90
    3
    0.86
    5
    0.82
    ных
    0.80
    9
    0.78
    0
    0.77
    dados
    0.75
    Act Density 0.002%

    No Known Activations