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

    Neuronpedia

    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    릅
    -0.07
    柩
    -0.07
     drafted
    -0.07
    /log
    -0.07
    一艘
    -0.07
     ceremon
    -0.07
    datepicker
    -0.07
    ⇾
    -0.07
    ACHI
    -0.07
     cé
    -0.07
    POSITIVE LOGITS
     curse
    0.07
     Barack
    0.07
    數
    0.07
    plugins
    0.07
    舉
    0.06
     Supporting
    0.06
     anew
    0.06
     Tracks
    0.06
    ular
    0.06
    ev
    0.06
    Act Density 0.022%

    No Known Activations