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

    Neuronpedia

    INDEX
    Explanations

    China

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oe
    -0.07
    ELCOME
    -0.07
     לך
    -0.07
     miłości
    -0.07
    xAA
    -0.06
    Decor
    -0.06
     đôi
    -0.06
    ervo
    -0.06
    华丽
    -0.06
    riott
    -0.06
    POSITIVE LOGITS
    توز
    0.07
     لبن
    0.07
    理智
    0.06
    suffix
    0.06
    还真是
    0.06
     Gibbs
    0.06
    sie
    0.06
    election
    0.06
    rib
    0.06
     shutting
    0.06
    Act Density 0.011%

    No Known Activations