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

    Neuronpedia

    INDEX
    Explanations

    days and weeks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    나
    -0.07
    /exec
    -0.07
    糖
    -0.07
     Bugün
    -0.07
    REQ
    -0.06
    火
    -0.06
    амет
    -0.06
     krev
    -0.06
    ingles
    -0.06
     причина
    -0.06
    POSITIVE LOGITS
     Easter
    0.09
     undertaken
    0.07
     відкрит
    0.07
    Â
    0.06
    erc
    0.06
     reusable
    0.06
     Lent
    0.06
    masked
    0.06
     Illustrated
    0.06
    ――――
    0.06
    Act Density 0.002%

    No Known Activations