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

    Neuronpedia

    INDEX
    Explanations

    crossorigin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IM
    -0.08
     державної
    -0.07
     našeho
    -0.07
    bao
    -0.06
    (ms
    -0.06
     snaží
    -0.06
    /big
    -0.06
     계속
    -0.06
     měli
    -0.06
     (*((
    -0.06
    POSITIVE LOGITS
     crossorigin
    0.10
    OUS
    0.07
    IVER
    0.06
     employing
    0.06
     acl
    0.06
    イツ
    0.06
    .Db
    0.06
    WithError
    0.06
    ्ग
    0.06
    кан
    0.06
    Act Density 0.001%

    No Known Activations