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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fieldName
    -0.06
     Fu
    -0.06
     '')
    -0.06
     kiếm
    -0.06
     consequat
    -0.06
     Ordinary
    -0.06
     dönem
    -0.06
     geopol
    -0.06
    opup
    -0.06
     برخی
    -0.06
    POSITIVE LOGITS
    (av
    0.07
    юк
    0.06
    ,char
    0.06
    ीज
    0.06
     �
    0.06
    (ast
    0.06
     применя
    0.06
     ########
    0.06
    ακ
    0.06
    Một
    0.06
    Act Density 0.019%

    No Known Activations