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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    微信
    -0.07
    电力
    -0.07
     hasn
    -0.07
     haven
    -0.07
     tying
    -0.07
    区块链
    -0.07
     WK
    -0.07
     grabbing
    -0.06
     מקצועי
    -0.06
    _log
    -0.06
    POSITIVE LOGITS
     rises
    0.08
     ראוי
    0.07
     redirection
    0.07
    보다
    0.07
    father
    0.07
    更低
    0.07
     remed
    0.07
    ℏ
    0.07
    رحم
    0.07
    פש
    0.07
    Act Density 0.052%

    No Known Activations