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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unload
    -0.07
     containing
    -0.07
    leccion
    -0.06
     ani
    -0.06
    ідом
    -0.06
    "]."
    -0.06
    ائد
    -0.06
    \Bridge
    -0.06
    UIStoryboardSegue
    -0.06
    checks
    -0.06
    POSITIVE LOGITS
     wes
    0.08
    گیر
    0.07
    остат
    0.07
    	last
    0.07
     Gerald
    0.06
    range
    0.06
     stren
    0.06
    David
    0.06
    美
    0.06
    spa
    0.06
    Act Density 0.031%

    No Known Activations