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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rops
    -0.07
     draggable
    -0.06
    btn
    -0.06
    olic
    -0.06
    =[
    -0.06
    /im
    -0.06
     (;;
    -0.06
    øj
    -0.06
     intentions
    -0.05
    گی
    -0.05
    POSITIVE LOGITS
     Jacqu
    0.07
    Česk
    0.07
     půj
    0.06
     PERF
    0.06
    	sort
    0.06
    ология
    0.06
     poplat
    0.06
    	pthread
    0.06
     těž
    0.06
    OffsetTable
    0.06
    Act Density 0.009%

    No Known Activations