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

    Neuronpedia

    INDEX
    Explanations

    .POST

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plung
    -0.07
     apocalypse
    -0.07
    天才
    -0.07
    expo
    -0.07
     grill
    -0.06
     Gladiator
    -0.06
    oblin
    -0.06
     ug
    -0.06
    alyzer
    -0.06
    好转
    -0.06
    POSITIVE LOGITS
    发送
    0.08
    (answer
    0.07
     maritime
    0.07
    احت
    0.07
     Dickinson
    0.07
    扭矩
    0.07
    镈
    0.07
     resil
    0.07
    казан
    0.07
    emia
    0.07
    Act Density 0.001%

    No Known Activations