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

    Neuronpedia

    INDEX
    Explanations

    Requesting/lacking more information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAS
    -0.07
    GRID
    -0.07
    라고
    -0.06
    ору
    -0.06
    .Rectangle
    -0.06
    _second
    -0.06
    ันยายน
    -0.06
    рава
    -0.06
     cos
    -0.06
     colorful
    -0.06
    POSITIVE LOGITS
     Zam
    0.06
    enc
    0.06
    [vi
    0.06
     Terr
    0.06
    	override
    0.06
     ráno
    0.06
    wegian
    0.06
    [end
    0.06
    شود
    0.06
    (admin
    0.06
    Act Density 0.014%

    No Known Activations