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

    Neuronpedia

    INDEX
    Explanations

    negative events/outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    とした
    -0.07
    زة
    -0.06
    Returns
    -0.06
    疗
    -0.06
    建立
    -0.06
    عمل
    -0.06
    기술
    -0.06
     �
    -0.06
    ecture
    -0.06
    евер
    -0.06
    POSITIVE LOGITS
    .gender
    0.07
     shakes
    0.07
    .Signal
    0.07
     AutoMapper
    0.07
     Transactions
    0.06
    ospace
    0.06
     Consortium
    0.06
     Replies
    0.06
     irradi
    0.06
    .script
    0.06
    Act Density 0.043%

    No Known Activations