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

    Neuronpedia

    INDEX
    Explanations

    definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _currency
    -0.07
    ocytes
    -0.07
    vae
    -0.07
    otherapy
    -0.07
    使之
    -0.07
    接地气
    -0.06
    伐
    -0.06
     treasury
    -0.06
    ्र
    -0.06
    зыва
    -0.06
    POSITIVE LOGITS
     fiz
    0.08
    Exited
    0.07
    (@"
    0.07
    ();↵
    0.07
     Ips
    0.07
     port
    0.07
    اني
    0.07
    ࡐ
    0.07
    ᒍ
    0.06
    عرو
    0.06
    Act Density 0.838%

    No Known Activations