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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Course
    -0.06
    	include
    -0.06
    .integration
    -0.06
    _Path
    -0.06
    .INT
    -0.06
    _health
    -0.06
     Loft
    -0.06
     điện
    -0.06
    (E
    -0.06
    ريس
    -0.05
    POSITIVE LOGITS
    ampled
    0.07
     ihren
    0.07
    ww
    0.07
     verileri
    0.06
     lö
    0.06
     děti
    0.06
    мос
    0.06
    .flags
    0.06
    نگی
    0.06
    inary
    0.06
    Act Density 0.002%

    No Known Activations