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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pays
    -0.08
    文旅
    -0.07
     brushing
    -0.07
     screenshots
    -0.07
    bags
    -0.07
    Phys
    -0.07
    (graph
    -0.07
    propri
    -0.07
    ographically
    -0.07
    พบ
    -0.07
    POSITIVE LOGITS
    钌
    0.07
     keer
    0.07
    鉴
    0.07
     HDF
    0.07
    גע
    0.07
    祚
    0.06
    罍
    0.06
     creek
    0.06
    <hr
    0.06
    ritis
    0.06
    Act Density 0.006%

    No Known Activations