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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filt
    -0.07
     ink
    -0.07
     tho
    -0.06
    	Route
    -0.06
     conspir
    -0.06
    trinsic
    -0.06
     Source
    -0.06
     feat
    -0.06
     yayım
    -0.05
     Cast
    -0.05
    POSITIVE LOGITS
    &B
    0.07
     especially
    0.07
    <Category
    0.07
     是否
    0.07
    illum
    0.07
     AABB
    0.07
    ленно
    0.07
    statistics
    0.06
    τομα
    0.06
    members
    0.06
    Act Density 0.003%

    No Known Activations