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

    Neuronpedia

    INDEX
    Explanations

    THE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponsive
    -0.07
     الأن
    -0.07
    ộc
    -0.06
     renal
    -0.06
     Anthem
    -0.06
     Exclusive
    -0.06
    /operators
    -0.06
    μένοι
    -0.06
    iềm
    -0.06
     distant
    -0.06
    POSITIVE LOGITS
    /book
    0.06
     package
    0.06
    Contact
    0.06
     :,
    0.06
    (label
    0.06
     Freder
    0.06
     cousin
    0.06
     paramString
    0.06
    [field
    0.06
     skateboard
    0.06
    Act Density 0.000%

    No Known Activations