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

    Neuronpedia

    INDEX
    Explanations

    Personal anecdotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gal
    -0.06
     Guil
    -0.06
    oggler
    -0.06
     leuk
    -0.06
     Slam
    -0.06
    智能
    -0.06
    โก
    -0.06
     Option
    -0.06
    ام
    -0.06
    ILLE
    -0.06
    POSITIVE LOGITS
    Console
    0.07
    ている
    0.07
    .getConfig
    0.06
     subcontract
    0.06
     zlep
    0.06
    ального
    0.06
     prescribed
    0.06
    `='$
    0.06
     Celebrity
    0.06
     branded
    0.06
    Act Density 0.748%

    No Known Activations