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

    Neuronpedia

    INDEX
    Explanations

    pounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     распространен
    -0.07
    ﺪ
    -0.07
     finding
    -0.07
     distinguish
    -0.07
    ugu
    -0.07
    	Event
    -0.06
    غن
    -0.06
     smashing
    -0.06
     stormed
    -0.06
    »
    -0.06
    POSITIVE LOGITS
    スー�
    0.07
    パー�
    0.07
     Wy
    0.07
    basis
    0.07
    家用
    0.07
    粮油
    0.07
    寒假
    0.07
    篮板
    0.07
    好久
    0.07
     hefty
    0.07
    Act Density 0.003%

    No Known Activations