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

    Neuronpedia

    INDEX
    Explanations

    upon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catchy
    -0.07
    的话
    -0.07
    スト
    -0.07
    It
    -0.06
    ینگ
    -0.06
    'id
    -0.06
     codigo
    -0.06
    女
    -0.06
     분야
    -0.06
    128
    -0.06
    POSITIVE LOGITS
     upon
    0.12
     Upon
    0.10
    Upon
    0.09
     beneath
    0.08
    upon
    0.08
    .up
    0.07
    uant
    0.07
     SetUp
    0.07
     Through
    0.07
    .setUp
    0.07
    Act Density 0.033%

    No Known Activations