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

    Neuronpedia

    INDEX
    Explanations

    legal changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contracts
    -0.07
    िवस
    -0.07
    αρ
    -0.07
    ्कर
    -0.07
     bedding
    -0.06
    وية
    -0.06
    PK
    -0.06
    지를
    -0.06
    Side
    -0.06
     contracting
    -0.06
    POSITIVE LOGITS
     왜
    0.07
     ไป
    0.06
     ElseIf
    0.06
     commenter
    0.06
     Wonderful
    0.06
     holy
    0.06
    (ins
    0.06
     qw
    0.06
     Orioles
    0.05
    .Speed
    0.05
    Act Density 0.041%

    No Known Activations