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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﮊ
    -0.08
    	Register
    -0.07
    	class
    -0.07
    intent
    -0.07
     withd
    -0.07
     mixin
    -0.07
    "E
    -0.06
    (join
    -0.06
    浓浓
    -0.06
    className
    -0.06
    POSITIVE LOGITS
    衾
    0.08
    cly
    0.07
    Ip
    0.07
    crap
    0.07
    ua
    0.07
    生猪
    0.07
    .har
    0.07
    汽车产业
    0.07
    地产
    0.07
    arbon
    0.07
    Act Density 0.003%

    No Known Activations