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

    Neuronpedia

    INDEX
    Explanations

    Code symbols/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Americas
    -0.07
    mpi
    -0.07
    @n
    -0.07
     پرد
    -0.07
    Physical
    -0.06
    �
    -0.06
    ��이터
    -0.06
     Charter
    -0.06
    lish
    -0.06
     northeast
    -0.06
    POSITIVE LOGITS
    �
    0.06
     squeez
    0.06
    ,node
    0.06
    保护
    0.06
    	ext
    0.06
     infield
    0.06
    进
    0.06
    ﾑ
    0.06
     ribs
    0.06
    )**
    0.06
    Act Density 0.008%

    No Known Activations