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

    Neuronpedia

    INDEX
    Explanations

    surreal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SwiftUI
    -0.07
     condemning
    -0.07
     ordinance
    -0.07
     ratings
    -0.06
     label
    -0.06
     Hotels
    -0.06
     nuclear
    -0.06
     wagon
    -0.06
     Plants
    -0.06
     Detective
    -0.06
    POSITIVE LOGITS
     surrendered
    0.08
     surrender
    0.07
    둥
    0.07
    dre
    0.07
    esseract
    0.07
     韓
    0.07
    かり
    0.07
    isse
    0.06
    ーラ
    0.06
     مى
    0.06
    Act Density 0.003%

    No Known Activations