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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tử
    -0.07
    �
    -0.07
     مق
    -0.06
    ětí
    -0.06
     게
    -0.06
    ---↵↵
    -0.06
    電視
    -0.06
    手に
    -0.06
     сосед
    -0.06
     packages
    -0.06
    POSITIVE LOGITS
    /%
    0.07
     buffer
    0.06
     redeemed
    0.06
    REFERRED
    0.06
     synonymous
    0.06
    secondary
    0.06
     Organic
    0.06
    _OPENGL
    0.06
    esian
    0.06
     Afghanistan
    0.06
    Act Density 0.040%

    No Known Activations