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

    Neuronpedia

    INDEX
    Explanations

    preserve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ραν
    -0.07
    toHaveBeenCalledTimes
    -0.07
     [("
    -0.07
    ало
    -0.06
     เ
    -0.06
     Đảng
    -0.06
     ISPs
    -0.06
    湖
    -0.06
    思想
    -0.06
     Otherwise
    -0.06
    POSITIVE LOGITS
    -js
    0.07
    executable
    0.07
    /kernel
    0.06
    	port
    0.06
     carbon
    0.06
     Penn
    0.06
     assass
    0.06
    θερ
    0.06
    totals
    0.06
    $current
    0.06
    Act Density 0.010%

    No Known Activations