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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    んど
    -0.07
    盯
    -0.07
     <*
    -0.07
    ܝ
    -0.07
    ᠡ
    -0.07
    .GetAxis
    -0.06
    放眼
    -0.06
     uyar
    -0.06
     climbed
    -0.06
    🌳
    -0.06
    POSITIVE LOGITS
    pageNumber
    0.08
    初中
    0.07
     ZX
    0.07
    	test
    0.07
     standpoint
    0.07
     first
    0.06
     ni
    0.06
     punches
    0.06
     semiconductor
    0.06
    食堂
    0.06
    Act Density 0.001%

    No Known Activations