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

    Neuronpedia

    INDEX
    Explanations

    Data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forest
    -0.07
     منذ
    -0.07
    ？↵↵
    -0.06
    _chat
    -0.06
    	base
    -0.06
    /aws
    -0.06
     rode
    -0.06
     шт
    -0.06
    .lab
    -0.06
    .Some
    -0.06
    POSITIVE LOGITS
     lic
    0.06
    (utf
    0.06
    ReadStream
    0.06
     equalTo
    0.06
    _pcm
    0.06
    -categories
    0.06
     берем
    0.06
     jp
    0.06
    Yii
    0.06
    entrant
    0.06
    Act Density 0.011%

    No Known Activations