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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кри
    -0.06
     yaw
    -0.06
    Activ
    -0.06
     minX
    -0.06
    -La
    -0.06
     epoch
    -0.06
    oundingBox
    -0.06
    허
    -0.06
     sku
    -0.05
     Canary
    -0.05
    POSITIVE LOGITS
     relied
    0.08
     國
    0.07
     dangerously
    0.07
     proving
    0.07
     creo
    0.07
    	c
    0.06
     المعلومات
    0.06
     BIO
    0.06
    aż
    0.06
     patiently
    0.06
    Act Density 0.001%

    No Known Activations