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

    Neuronpedia

    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Su
    -0.07
     Buddy
    -0.06
    HTMLElement
    -0.06
     alas
    -0.06
    dojo
    -0.06
    Truth
    -0.06
    _model
    -0.06
    Points
    -0.06
     When
    -0.06
     Michaels
    -0.06
    POSITIVE LOGITS
    水平
    0.06
    ainties
    0.06
     zer
    0.06
    ीच
    0.06
    …↵
    0.06
     прибор
    0.06
    _ERR
    0.06
    ordination
    0.06
    ните
    0.06
    업체
    0.06
    Act Density 0.031%

    No Known Activations