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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ión
    -0.07
     boosts
    -0.07
    ندي
    -0.07
     chiế
    -0.07
    ponents
    -0.06
    Segment
    -0.06
    ую
    -0.06
    precedented
    -0.06
     Parse
    -0.06
    ivity
    -0.06
    POSITIVE LOGITS
    once
    0.07
     pointless
    0.07
     MASTER
    0.07
     arr
    0.07
    黎
    0.06
    	DBG
    0.06
     ngoại
    0.06
     MCC
    0.06
    (zip
    0.06
     비밀
    0.06
    Act Density 0.023%

    No Known Activations