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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reat
    -0.07
     podium
    -0.07
    =date
    -0.07
     Κά
    -0.07
     sharp
    -0.07
     userId
    -0.07
     áreas
    -0.07
    _MIDDLE
    -0.07
     todas
    -0.07
    设计
    -0.07
    POSITIVE LOGITS
     owing
    0.12
     owe
    0.08
     Ow
    0.07
     owes
    0.07
     owed
    0.07
     thankful
    0.06
     Hawkins
    0.06
     OW
    0.06
     winnings
    0.06
     CLIIIK
    0.06
    Act Density 0.005%

    No Known Activations