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

    Neuronpedia

    INDEX
    Explanations

    ".zip" files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    منتدى
    -0.08
    хи
    -0.07
    】
    -0.07
    midt
    -0.07
    	mysql
    -0.07
    mysql
    -0.07
    	reply
    -0.07
    )
↵
    -0.07
    interaction
    -0.06
    }),
    -0.06
    POSITIVE LOGITS
     worst
    0.07
    雾
    0.07
     kup
    0.07
     wolf
    0.07
    猬
    0.07
    izzly
    0.07
     kom
    0.07
    榛
    0.07
    胡子
    0.07
    絷
    0.06
    Act Density 0.002%

    No Known Activations