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

    Neuronpedia

    INDEX
    Explanations

    self.attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Découvrez
    0.86
     CONTENTS
    0.72
     내용
    0.71
    ुअल
    0.68
    ható
    0.68
     Bedürfn
    0.68
    ността
    0.67
     Continental
    0.67
     powiet
    0.66
     ؟
    0.66
    POSITIVE LOGITS
    ._
    1.15
    .__
    0.93
    ->_
    0.92
    .-
    0.81
    .$
    0.76
    .___
    0.68
    bibitem
    0.68
    :_
    0.67
     ricon
    0.66
    सेशन
    0.66
    Act Density 0.169%

    No Known Activations