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

    Neuronpedia

    INDEX
    Explanations

    panel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çalışm
    -0.07
    _elems
    -0.07
    高职
    -0.07
    院长
    -0.07
     Cassidy
    -0.07
    _when
    -0.07
    アジア
    -0.06
    涔
    -0.06
    ޤ
    -0.06
     Dataset
    -0.06
    POSITIVE LOGITS
    翻
    0.08
     garant
    0.07
     trademark
    0.07
    收取
    0.07
     button
    0.07
    Bid
    0.07
    暴雨
    0.07
     enumeration
    0.07
     ol
    0.07
     landmark
    0.06
    Act Density 0.012%

    No Known Activations