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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     누
    -0.06
     �
    -0.06
    (ff
    -0.06
     gui
    -0.06
    teki
    -0.06
     Brands
    -0.06
     теперь
    -0.06
    	a
    -0.06
    洞
    -0.06
    ，加
    -0.05
    POSITIVE LOGITS
    ніцип
    0.07
     BA
    0.07
     miracle
    0.07
     uč
    0.07
    .ep
    0.06
     Precision
    0.06
    '/>↵
    0.06
     getir
    0.06
     urlparse
    0.06
    alyze
    0.06
    Act Density 0.133%

    No Known Activations