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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Holder
    -0.09
    ﹩
    -0.08
    佗
    -0.07
    楞
    -0.07
    传统产业
    -0.07
    弩
    -0.07
     בכל
    -0.07
    流星
    -0.07
    盒子
    -0.07
    虹
    -0.07
    POSITIVE LOGITS
     madre
    0.09
    xbf
    0.07
     adaptations
    0.07
    	inst
    0.07
     HSV
    0.07
    Treatment
    0.07
    tests
    0.07
     advisers
    0.07
    (config
    0.06
    .final
    0.06
    Act Density 0.168%

    No Known Activations