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

    Neuronpedia

    INDEX
    Explanations

    Time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attainment
    -0.06
     personnes
    -0.06
    =tmp
    -0.06
    FromArray
    -0.06
    Patterns
    -0.06
    	top
    -0.06
    rian
    -0.06
    ock
    -0.06
     Glass
    -0.06
     RUNNING
    -0.06
    POSITIVE LOGITS
    "/><
    0.08
    ‐-
    0.07
     gł
    0.06
    さ
    0.06
    �
    0.06
    #=
    0.06
    ffiti
    0.06
     skoro
    0.06
     intox
    0.06
     يع
    0.06
    Act Density 0.002%

    No Known Activations