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

    Neuronpedia

    INDEX
    Explanations

    denoising and noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.85
    mA
    0.75
    cludes
    0.75
    𝓑
    0.72
    ym
    0.72
    Area
    0.71
    rait
    0.71
    mW
    0.71
    니다
    0.70
    "।
    0.70
    POSITIVE LOGITS
     hiểm
    0.97
     Armenians
    0.82
     Armenian
    0.80
     Yeats
    0.79
     ίδ
    0.79
     небольшой
    0.77
     Soho
    0.76
     البطولة
    0.76
     τ
    0.74
    光学
    0.74
    Act Density 0.002%

    No Known Activations