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

    Neuronpedia

    INDEX
    Explanations

    Schedules and biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENV
    -0.07
     printk
    -0.06
     lately
    -0.06
    REQUIRED
    -0.06
    jak
    -0.06
     صفحه
    -0.06
     swaps
    -0.06
    .]
    -0.06
    έας
    -0.06
    awesome
    -0.06
    POSITIVE LOGITS
    ्दर
    0.07
    _SIM
    0.07
     alien
    0.06
     succ
    0.06
    (pt
    0.06
     fleet
    0.06
     hydro
    0.06
    omm
    0.06
     calor
    0.06
    oki
    0.06
    Act Density 0.361%

    No Known Activations