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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Txt
    -0.07
    大连
    -0.07
    فجر
    -0.07
    קס
    -0.07
     Covers
    -0.07
    粲
    -0.07
    Ń
    -0.07
    橘
    -0.06
     WLAN
    -0.06
    _________________↵↵
    -0.06
    POSITIVE LOGITS
     muit
    0.08
     visas
    0.06
    狃
    0.06
    עביר
    0.06
     intends
    0.06
    wh
    0.06
    iphery
    0.06
    _app
    0.06
    execute
    0.06
    ﯡ
    0.06
    Act Density 0.027%

    No Known Activations