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

    Neuronpedia

    INDEX
    Explanations

    Numbers in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Fatalf
    -0.07
    .display
    -0.07
    acağım
    -0.07
    =output
    -0.06
    ofstream
    -0.06
     Naw
    -0.06
    Design
    -0.06
    deny
    -0.06
     Design
    -0.06
     Dexter
    -0.06
    POSITIVE LOGITS
     serialize
    0.07
     απο
    0.06
     orally
    0.06
    (second
    0.06
     num
    0.06
     dem
    0.06
     economists
    0.06
     Replies
    0.06
     ap
    0.06
     dabei
    0.06
    Act Density 0.004%

    No Known Activations