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

    Neuronpedia

    INDEX
    Explanations

    mindful of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.97
    /
    0.92
     organi
    0.86
    ning
    0.84
    s
    0.83
     n
    0.77
    is
    0.77
    rain
    0.75
    I
    0.74
    room
    0.73
    POSITIVE LOGITS
    Tarefa
    0.95
    вета
    0.90
    tarea
    0.88
    。
    0.88
     リ
    0.84
    、“
    0.81
    。【
    0.81
    тиву
    0.80
    Karte
    0.80
    Transaksi
    0.80
    Act Density 0.003%

    No Known Activations