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

    Neuronpedia

    INDEX
    Explanations

    rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ref
    -0.08
     Аз
    -0.07
     leng
    -0.07
     trousers
    -0.07
    iram
    -0.06
     Dai
    -0.06
    ��
    -0.06
     imposing
    -0.06
    emale
    -0.06
    _MOBILE
    -0.06
    POSITIVE LOGITS
     Picks
    0.06
     Action
    0.06
     Cheese
    0.06
    藝
    0.06
     initData
    0.06
     dafür
    0.06
    '/>↵
    0.06
     Builders
    0.06
     Fritz
    0.06
     bananas
    0.06
    Act Density 0.008%

    No Known Activations