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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WN
    -0.07
    न
    -0.06
     Entr
    -0.06
    oogle
    -0.06
    ARGS
    -0.06
     CEL
    -0.06
    申请
    -0.06
    ’ya
    -0.06
    зу
    -0.06
    าญ
    -0.06
    POSITIVE LOGITS
    ่อม
    0.07
    itel
    0.07
    ritional
    0.06
     Gaul
    0.06
     letras
    0.06
     nisi
    0.06
     joueur
    0.06
     wil
    0.06
     Fach
    0.06
     omdat
    0.06
    Act Density 0.049%

    No Known Activations