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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .openapi
    -0.07
    隆
    -0.07
    roken
    -0.07
    ưởng
    -0.07
     belonging
    -0.07
    igram
    -0.07
    (node
    -0.06
    ülük
    -0.06
    ulous
    -0.06
     образования
    -0.06
    POSITIVE LOGITS
     UN
    0.07
     COLL
    0.07
    	EIF
    0.07
     Purs
    0.06
     woven
    0.06
     проведення
    0.06
    AEA
    0.06
     différents
    0.06
     EVT
    0.06
     retries
    0.06
    Act Density 0.015%

    No Known Activations