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

    Neuronpedia

    INDEX
    Explanations

    engineering systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヘ
    -0.06
     Lease
    -0.06
    (Collision
    -0.06
    .zz
    -0.06
    _species
    -0.06
     механи
    -0.06
     객체
    -0.06
    ведите
    -0.06
     comercial
    -0.06
    orado
    -0.06
    POSITIVE LOGITS
     Pension
    0.08
     dropped
    0.07
    DAL
    0.07
     pension
    0.07
    ples
    0.06
     Eins
    0.06
     وإ
    0.06
    _credentials
    0.06
    -com
    0.06
     Rolled
    0.06
    Act Density 0.166%

    No Known Activations