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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    allenges
    -0.07
    (Display
    -0.07
    창
    -0.07
    /sw
    -0.06
    iydi
    -0.06
    pike
    -0.06
     Boxes
    -0.06
     rotating
    -0.06
    であ
    -0.06
    toolbox
    -0.06
    POSITIVE LOGITS
     Brittany
    0.07
     Loc
    0.06
     ","
    0.06
    classify
    0.06
    (sql
    0.06
     přem
    0.06
    恩
    0.06
    ACH
    0.06
    _,
    0.06
     firearms
    0.06
    Act Density 0.000%

    No Known Activations