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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timestamps
    -0.07
    �
    -0.07
    th
    -0.06
     Report
    -0.06
    不斷
    -0.06
    怎么样
    -0.06
    thinking
    -0.06
     set
    -0.06
    ți
    -0.06
     sudah
    -0.06
    POSITIVE LOGITS
     generals
    0.09
     GObject
    0.08
    全校
    0.07
    셴
    0.07
     الفترة
    0.07
    ятся
    0.07
     Salman
    0.07
     clinics
    0.07
    \xd
    0.07
    مشاريع
    0.07
    Act Density 0.003%

    No Known Activations