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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaybet
    -0.07
    iyatı
    -0.07
    nonce
    -0.06
    children
    -0.06
        
    -0.06
    economic
    -0.06
    Ö
    -0.06
     UNESCO
    -0.06
    ('/:
    -0.06
    bitrary
    -0.06
    POSITIVE LOGITS
     atroc
    0.07
    ाहरण
    0.07
     pending
    0.06
     Ren
    0.06
    .Popen
    0.06
     đốc
    0.06
     ran
    0.06
    ecause
    0.06
     analyst
    0.06
     travels
    0.06
    Act Density 0.029%

    No Known Activations