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

    Neuronpedia

    INDEX
    Explanations

    image file extensions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nivel
    0.48
     producto
    0.46
     Zara
    0.46
     Boga
    0.46
     acc
    0.45
     efect
    0.45
     servici
    0.45
     wood
    0.44
     cometido
    0.44
     justices
    0.44
    POSITIVE LOGITS
    лаб
    0.51
    бай
    0.49
    图
    0.48
    ал
    0.47
    Су
    0.45
    要注意
    0.45
    其他
    0.44
    ҹ
    0.44
    在
    0.44
    后
    0.43
    Act Density 0.001%

    No Known Activations