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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GEO
    -0.07
    .EXTRA
    -0.06
     Herb
    -0.06
    .Order
    -0.06
     Nach
    -0.06
     ORDER
    -0.06
    нів
    -0.06
     flash
    -0.06
    ्व
    -0.06
    ате
    -0.06
    POSITIVE LOGITS
    提升
    0.07
    _combine
    0.06
    mailto
    0.06
     ContentValues
    0.06
     association
    0.06
    랫
    0.06
    _link
    0.06
     текущ
    0.06
     yiy
    0.06
     guideline
    0.06
    Act Density 0.037%

    No Known Activations