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

    Neuronpedia

    INDEX
    Explanations

    to research and funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๒
    0.46
    Hlav
    0.43
    ínguez
    0.42
    èce
    0.41
    问道
    0.40
    üğü
    0.40
    ürdig
    0.40
    牫
    0.40
    ༠
    0.40
    исто
    0.39
    POSITIVE LOGITS
     from
    0.59
     on
    0.51
     with
    0.49
     to
    0.47
     for
    0.47
     within
    0.45
     out
    0.44
     in
    0.43
     when
    0.43
     från
    0.43
    Act Density 0.249%

    No Known Activations