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

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woff
    -0.07
    裈
    -0.07
     фев
    -0.07
    Ӣ
    -0.06
    (Encoding
    -0.06
    bst
    -0.06
     اله
    -0.06
    Nach
    -0.06
     roles
    -0.06
    爟
    -0.06
    POSITIVE LOGITS
     Trade
    0.08
     Compar
    0.08
    Clark
    0.07
     change
    0.07
     nova
    0.07
    _uniform
    0.07
    (dec
    0.07
     abnormal
    0.07
     JC
    0.07
     Lowell
    0.07
    Act Density 0.063%

    No Known Activations