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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sympathy
    -0.07
     WATER
    -0.07
    (None
    -0.07
    Worker
    -0.06
     exposures
    -0.06
    kę
    -0.06
     Osama
    -0.06
    TJ
    -0.06
    -module
    -0.06
     knockout
    -0.06
    POSITIVE LOGITS
    enerated
    0.07
    tryside
    0.06
    ……………………
    0.06
     abc
    0.06
    fortunately
    0.06
    regn
    0.06
     Railroad
    0.06
     ----------------
    0.06
     periodically
    0.06
     今
    0.06
    Act Density 0.059%

    No Known Activations