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

    Neuronpedia

    INDEX
    Explanations

    district

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Get
    -0.07
    My
    -0.06
    \(
    -0.06
    Git
    -0.06
     is
    -0.06
    	rd
    -0.06
    Los
    -0.06
    They
    -0.06
     всей
    -0.06
    _{
    -0.06
    POSITIVE LOGITS
     WT
    0.07
    _exe
    0.07
     insured
    0.07
     resident
    0.07
    κτη
    0.06
     Cumhurbaşkanı
    0.06
    uint
    0.06
     طبقه
    0.06
    REP
    0.06
    roti
    0.06
    Act Density 0.319%

    No Known Activations