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

    Neuronpedia

    INDEX
    Explanations

    Widespread presence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etype
    -0.07
    azing
    -0.06
     标
    -0.06
    asured
    -0.06
    	process
    -0.06
    ün
    -0.06
    elope
    -0.06
    "...
    -0.06
    스트
    -0.06
    ,↵↵↵↵
    -0.06
    POSITIVE LOGITS
     guarantees
    0.07
     sona
    0.07
    mez
    0.07
     chân
    0.06
    wow
    0.06
     зависим
    0.06
     Console
    0.06
     notebook
    0.06
     десят
    0.06
    AppDelegate
    0.06
    Act Density 0.102%

    No Known Activations