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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	card
    -0.06
    floor
    -0.06
    懂
    -0.06
     chatt
    -0.06
     HANDLE
    -0.05
     planta
    -0.05
     nurs
    -0.05
    spa
    -0.05
     Recru
    -0.05
    幼
    -0.05
    POSITIVE LOGITS
    lobals
    0.07
     число
    0.07
    .getMethod
    0.07
    %"↵
    0.07
     perfectly
    0.07
    (JSONObject
    0.07
    اسي
    0.06
     Ng
    0.06
     오
    0.06
     treffen
    0.06
    Act Density 0.000%

    No Known Activations