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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =========
    -0.07
    SHOW
    -0.07
     rails
    -0.07
     İyi
    -0.07
     timeouts
    -0.07
     жінок
    -0.06
    }`}
    -0.06
    视频
    -0.06
     zosta
    -0.06
    _orders
    -0.06
    POSITIVE LOGITS
     Lif
    0.07
     Michele
    0.06
     baker
    0.06
    Chan
    0.06
     EntryPoint
    0.06
    <path
    0.06
    chan
    0.06
    urban
    0.06
    .infinity
    0.06
     Conc
    0.05
    Act Density 0.091%

    No Known Activations