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

    Neuronpedia

    INDEX
    Explanations

    certification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uin
    -0.07
    usto
    -0.07
     Napoleon
    -0.06
     지난
    -0.06
     compte
    -0.06
    636
    -0.06
    uft
    -0.06
     Utah
    -0.06
     результат
    -0.06
     Og
    -0.06
    POSITIVE LOGITS
    testing
    0.07
    (mock
    0.07
    ิเคราะห
    0.06
    ับร
    0.06
     stir
    0.06
     vpn
    0.06
     Railway
    0.06
    ται
    0.06
     Test
    0.06
    Desk
    0.06
    Act Density 0.023%

    No Known Activations