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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EMS
    -0.09
     Walker
    -0.07
     Islamist
    -0.07
    lux
    -0.07
    _Arg
    -0.07
    _FN
    -0.07
    ลาด
    -0.06
    interest
    -0.06
    	location
    -0.06
    bal
    -0.06
    POSITIVE LOGITS
     lashes
    0.07
    арамет
    0.06
     παρ
    0.06
     ром
    0.06
     dwind
    0.06
    imestamp
    0.06
     vazgeç
    0.06
     �
    0.06
     subscribe
    0.06
     Caption
    0.06
    Act Density 0.114%

    No Known Activations