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

    Neuronpedia

    INDEX
    Explanations

    displays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oun
    -0.08
     partner
    -0.07
     },
    -0.07
    	loop
    -0.07
    .Fetch
    -0.07
    erva
    -0.06
     curtain
    -0.06
     teardown
    -0.06
     guaranteed
    -0.06
     Chicago
    -0.06
    POSITIVE LOGITS
     displays
    0.24
     Displays
    0.12
    Displays
    0.11
    Founded
    0.07
    mainwindow
    0.07
    _STS
    0.06
    ंड
    0.06
     dread
    0.06
    "P
    0.06
    ABCDEFG
    0.06
    Act Density 0.006%

    No Known Activations