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

    Neuronpedia

    INDEX
    Explanations

    Character appearance in fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pdev
    -0.07
     خرید
    -0.06
     workshops
    -0.06
    чих
    -0.06
     дод
    -0.06
     PlayStation
    -0.06
     웨
    -0.06
     bitterness
    -0.06
     puppet
    -0.06
    ίου
    -0.06
    POSITIVE LOGITS
    Como
    0.06
    /tasks
    0.06
     SOUND
    0.06
    โร
    0.06
    (Environment
    0.06
    RULE
    0.06
     Bar
    0.06
     않은
    0.06
    >]
    0.06
    ])+
    0.06
    Act Density 0.039%

    No Known Activations