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

    Neuronpedia

    INDEX
    Explanations

    questions and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    0.54
    EL
    0.50
    AN
    0.49
    ie
    0.49
    LER
    0.48
    P
    0.48
    H
    0.46
    HR
    0.46
    att
    0.45
    M
    0.45
    POSITIVE LOGITS
     sapon
    0.55
     DID
    0.49
     derogatory
    0.49
     Gazprom
    0.49
     Citibank
    0.49
     fraudulent
    0.48
    詐
    0.48
     fraudsters
    0.48
    ibrate
    0.48
     newbies
    0.47
    Act Density 0.001%

    No Known Activations