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

    Neuronpedia

    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .`,↵
    -0.07
    ниці
    -0.07
    sss
    -0.06
    .remaining
    -0.06
    仅
    -0.06
    roud
    -0.06
     christian
    -0.06
     academic
    -0.06
    Upon
    -0.06
     certificate
    -0.06
    POSITIVE LOGITS
    Atlanta
    0.07
    Effects
    0.06
    added
    0.06
     elé
    0.06
    zens
    0.06
    0.06
    ратить
    0.06
    ленный
    0.06
    気持ち
    0.06
     spat
    0.06
    Act Density 0.076%

    No Known Activations