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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    empty
    -0.07
    ानव
    -0.06
    female
    -0.06
     Steel
    -0.06
     exceptional
    -0.06
     Moderator
    -0.06
     youngest
    -0.06
    fra
    -0.06
     Control
    -0.06
     fried
    -0.06
    POSITIVE LOGITS
    .::.::
    0.07
    csrf
    0.07
    ()},↵
    0.07
    []>(
    0.06
     vysok
    0.06
    ("/",
    0.06
     Sır
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
    un
    0.06
    izzling
    0.06
    Act Density 0.003%

    No Known Activations