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

    Neuronpedia

    INDEX
    Explanations

    hourly, daily, or by day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     никакого
    0.50
     micrófono
    0.45
     женой
    0.43
    Termination
    0.43
    ין
    0.41
    укра
    0.41
    VIR
    0.41
    に
    0.41
    ิทธิภาพ
    0.41
    旦
    0.41
    POSITIVE LOGITS
     aa
    0.47
     योर
    0.47
     History
    0.46
    able
    0.45
    ed
    0.44
     dal
    0.44
    刓
    0.43
     discounts
    0.43
     Who
    0.42
     snar
    0.42
    Act Density 0.000%

    No Known Activations