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

    Neuronpedia

    INDEX
    Explanations

    driven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SX
    -0.07
    вания
    -0.06
     Vaugh
    -0.06
     memoir
    -0.06
     Titanic
    -0.06
     ноч
    -0.06
     AC
    -0.06
     lighten
    -0.06
    otes
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     ورزش
    0.08
    핀
    0.07
     greedy
    0.07
    攻
    0.07
     перел
    0.07
    gran
    0.06
    .Inner
    0.06
    惠
    0.06
    .unlock
    0.06
    results
    0.06
    Act Density 0.003%

    No Known Activations