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

    Neuronpedia

    INDEX
    Explanations

    Mathematica code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )를
    -0.07
     süre
    -0.07
     bunu
    -0.06
     briefly
    -0.06
     dealt
    -0.06
     reliably
    -0.06
     đời
    -0.06
     Accordingly
    -0.06
     hab
    -0.06
     걸
    -0.06
    POSITIVE LOGITS
    [{
    0.22
    ancouver
    0.08
    ANT
    0.07
     Hampshire
    0.07
    .PORT
    0.07
    ΑΝΤ
    0.07
    город
    0.06
    """),↵
    0.06
    Toronto
    0.06
    министра
    0.06
    Act Density 0.001%

    No Known Activations