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

    Neuronpedia

    INDEX
    Explanations

    never

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Jones
    -0.07
    緊
    -0.07
     بس
    -0.07
     orderBy
    -0.07
    (strings
    -0.06
    Assets
    -0.06
    ��态
    -0.06
     diarrhea
    -0.06
    ΟΛ
    -0.06
    紧
    -0.06
    POSITIVE LOGITS
    como
    0.06
    .loc
    0.06
     never
    0.06
    ,mid
    0.06
     perí
    0.06
    IndexPath
    0.06
    ».↵↵
    0.06
     recommends
    0.06
    ERNEL
    0.06
     refl
    0.06
    Act Density 0.020%

    No Known Activations