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

    Neuronpedia

    INDEX
    Explanations

    youtuber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гры
    0.39
     [@
    0.38
    傆
    0.38
    qli
    0.38
     আবদুল্লাহ
    0.37
     arriba
    0.37
     ovale
    0.37
    assay
    0.37
    hões
    0.36
    haram
    0.36
    POSITIVE LOGITS
     tubers
    0.98
    Tub
    0.97
     tuber
    0.95
     tube
    0.93
     Tub
    0.93
    tub
    0.93
    Tube
    0.89
     Tube
    0.86
     tub
    0.86
    tube
    0.83
    Act Density 0.003%

    No Known Activations