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

    Neuronpedia

    INDEX
    Explanations

    equilibrium or lasting impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flagged
    -0.07
     `$
    -0.06
     Julio
    -0.06
     कल
    -0.06
     nickel
    -0.06
     toReturn
    -0.06
     phiếu
    -0.06
    �
    -0.06
    fld
    -0.06
     nxt
    -0.06
    POSITIVE LOGITS
    ilmektedir
    0.07
     호텔
    0.06
    、↵↵
    0.06
     анг
    0.06
     Marketplace
    0.06
    시는
    0.06
    (correct
    0.06
     добре
    0.06
     rooft
    0.06
    _FILES
    0.06
    Act Density 1.060%

    No Known Activations