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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infinite
    -0.07
    目的
    -0.07
     degraded
    -0.06
     اصلی
    -0.06
    에서의
    -0.06
     Contemporary
    -0.06
     highlighted
    -0.06
    Од
    -0.06
    _),
    -0.06
     sat
    -0.05
    POSITIVE LOGITS
    两
    0.08
    (HttpContext
    0.08
    兩
    0.07
    -last
    0.07
    .dst
    0.06
     第一
    0.06
    .csrf
    0.06
    	mc
    0.06
    ric
    0.06
    ΕΤ
    0.06
    Act Density 0.015%

    No Known Activations