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

    Neuronpedia

    INDEX
    Explanations

    Names in news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Damage
    -0.07
     jokes
    -0.07
    吸取
    -0.07
     الدكت
    -0.07
     darker
    -0.07
    /code
    -0.06
    正常
    -0.06
    enville
    -0.06
     ful
    -0.06
    诘
    -0.06
    POSITIVE LOGITS
     orc
    0.07
    (plan
    0.07
    erais
    0.07
     stash
    0.07
     hearings
    0.07
     roast
    0.07
    uthor
    0.07
     Miss
    0.06
     stirring
    0.06
     automobiles
    0.06
    Act Density 0.038%

    No Known Activations