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

    Neuronpedia

    INDEX
    Explanations

    operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airborne
    -0.07
     Lazy
    -0.07
     Caucasian
    -0.06
    Equals
    -0.06
     LEVEL
    -0.06
     debacle
    -0.06
    -items
    -0.06
     ном
    -0.06
     Written
    -0.06
    ιος
    -0.06
    POSITIVE LOGITS
     Braun
    0.07
    Rgb
    0.06
     contestant
    0.06
    GOR
    0.06
    .hist
    0.06
    LTE
    0.06
    mal
    0.06
    onto
    0.06
     outr
    0.06
     اطلاع
    0.06
    Act Density 0.000%

    No Known Activations