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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diagn
    -0.07
     stim
    -0.07
     Ray
    -0.07
     ninth
    -0.06
    ^(
    -0.06
     kickoff
    -0.06
     './
    -0.06
     binh
    -0.06
    (bbox
    -0.06
     faster
    -0.06
    POSITIVE LOGITS
     Else
    0.07
    SP
    0.07
    	sl
    0.07
    TRGL
    0.07
    ESP
    0.07
    etical
    0.07
    ugo
    0.06
     ELSE
    0.06
    usra
    0.06
    аш
    0.06
    Act Density 0.011%

    No Known Activations