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

    Neuronpedia

    INDEX
    Explanations

    except

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $data
    -0.08
     ملی
    -0.07
    \web
    -0.07
     государ
    -0.07
    Relative
    -0.07
    -grow
    -0.06
    ;width
    -0.06
     celui
    -0.06
    =format
    -0.06
    Naz
    -0.06
    POSITIVE LOGITS
     except
    0.09
    	except
    0.07
    except
    0.07
    Help
    0.07
     Devin
    0.07
    upa
    0.06
    \uC
    0.06
    Except
    0.06
     ext
    0.06
     Victims
    0.06
    Act Density 0.001%

    No Known Activations