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

    Neuronpedia

    INDEX
    Explanations

    margin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UME
    -0.06
    lfw
    -0.06
    ová
    -0.06
    感到
    -0.06
     و
    -0.06
    =u
    -0.06
     Orchard
    -0.06
     τό
    -0.06
     entityType
    -0.06
     حسین
    -0.05
    POSITIVE LOGITS
     行政
    0.07
     breaches
    0.07
    ',{'
    0.07
    stre
    0.07
    بي
    0.06
    .Auto
    0.06
     sparkling
    0.06
     frontier
    0.06
     libero
    0.06
    	offset
    0.06
    Act Density 0.005%

    No Known Activations