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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toilets
    -0.08
    ⬇
    -0.08
    %">↵
    -0.07
    .CheckedChanged
    -0.07
     towns
    -0.07
    .Pattern
    -0.07
    球员
    -0.07
     dollars
    -0.07
     Sitting
    -0.06
     Queens
    -0.06
    POSITIVE LOGITS
     btnCancel
    0.08
    הרש
    0.07
    (stderr
    0.07
    如实
    0.07
    ested
    0.07
    ('*
    0.07
    ("&
    0.06
     intim
    0.06
     revealing
    0.06
     setTitle
    0.06
    Act Density 2.649%

    No Known Activations