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

    Neuronpedia

    INDEX
    Explanations

    GUI components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minWidth
    -0.06
    poč
    -0.06
     ไม
    -0.06
    líd
    -0.06
     cock
    -0.06
     eing
    -0.06
    igaret
    -0.06
     ostat
    -0.06
    ()],↵
    -0.06
     brighter
    -0.06
    POSITIVE LOGITS
     영국
    0.07
    armor
    0.07
     unemployed
    0.07
     doors
    0.06
     Paşa
    0.06
     additionally
    0.06
    iction
    0.06
     Huyện
    0.06
    platz
    0.06
     त
    0.06
    Act Density 0.007%

    No Known Activations