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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psycho
    -0.07
     gravitational
    -0.07
     prefer
    -0.06
     Trials
    -0.06
     religious
    -0.06
     camar
    -0.06
    нош
    -0.06
     ज
    -0.06
     XIII
    -0.06
     progressives
    -0.06
    POSITIVE LOGITS
    .basic
    0.07
     대상
    0.07
    Messaging
    0.07
    Element
    0.06
    .ask
    0.06
     QApplication
    0.06
    ΡΙ
    0.06
    иться
    0.06
    end
    0.06
    hd
    0.06
    Act Density 0.003%

    No Known Activations