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

    Neuronpedia

    INDEX
    Explanations

    datetime.date objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िएंट
    0.95
    BeerItem
    0.86
     alegre
    0.86
    敝
    0.86
    籀
    0.86
    たちが
    0.85
    あえず
    0.84
     eag
    0.84
     eccles
    0.84
    哫
    0.84
    POSITIVE LOGITS
    ти
    0.97
    А
    0.92
    <0xB2>
    0.89
    си
    0.84
    ков
    0.82
    ру
    0.81
    ни
    0.81
    These
    0.80
    на
    0.78
    Ⲟ
    0.78
    Act Density 0.002%

    No Known Activations