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

    Neuronpedia

    INDEX
    Explanations

    peaks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liber
    -0.08
     continuity
    -0.07
    continu
    -0.07
     ultraviolet
    -0.07
    $("#
    -0.07
    measurement
    -0.07
    -Lo
    -0.07
    ro
    -0.07
    research
    -0.07
     incision
    -0.07
    POSITIVE LOGITS
     Fernandes
    0.09
     minib
    0.08
     cake
    0.08
     mergers
    0.08
    cake
    0.08
     Мін
    0.08
     MIN
    0.08
     मालिक
    0.08
     Künd
    0.08
     الأسرة
    0.08
    Act Density 0.022%

    No Known Activations