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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addictive
    -0.07
     subur
    -0.07
    ’hui
    -0.07
     rửa
    -0.07
     Hüs
    -0.07
     ملت
    -0.06
     destruction
    -0.06
     rebound
    -0.06
     ips
    -0.06
    .au
    -0.06
    POSITIVE LOGITS
    ')">
    0.06
    uffed
    0.06
    REFERENCE
    0.06
    낸
    0.06
    Liter
    0.06
    //================================================================
    0.06
     다시
    0.06
     この
    0.06
    нулась
    0.06
    auses
    0.06
    Act Density 0.006%

    No Known Activations