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

    Neuronpedia

    INDEX
    Explanations

    IP headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elim
    -0.09
    уы
    -0.08
     zabr
    -0.08
    _picker
    -0.08
    ANTED
    -0.08
    Suppress
    -0.07
     pity
    -0.07
    edicine
    -0.07
     Dropdown
    -0.07
     впечат
    -0.07
    POSITIVE LOGITS
     Cuando
    0.07
     $(".
    0.07
     propriedades
    0.07
     સામ
    0.07
     propiedades
    0.07
     Pflicht
    0.07
     dock
    0.07
     જ્યારે
    0.07
     cuando
    0.07
     ona
    0.07
    Act Density 0.001%

    No Known Activations