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
     acquaint
    -0.07
     republican
    -0.07
     reign
    -0.06
    egree
    -0.06
     alternatives
    -0.06
     hamburger
    -0.06
    plier
    -0.06
     waiver
    -0.06
     Odds
    -0.06
    活
    -0.06
    POSITIVE LOGITS
     จะ
    0.07
    (fullfile
    0.07
     typealias
    0.07
    (ActionEvent
    0.07
     "\
    0.06
    ution
    0.06
    /interfaces
    0.06
     ByteArrayInputStream
    0.06
    benh
    0.06
     cà
    0.06
    Act Density 0.002%

    No Known Activations