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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الزوج
    -0.09
     ies
    -0.09
    (filepath
    -0.09
     ঢ
    -0.08
     progr
    -0.08
    élé
    -0.08
    sti
    -0.08
     �
    -0.08
     programmi
    -0.08
     semb
    -0.08
    POSITIVE LOGITS
    =True
    0.10
    Specified
    0.10
    =None
    0.10
    ={'
    0.09
    =
    0.09
    ='
    0.09
    ={"
    0.08
    =False
    0.08
    =self
    0.08
    =lambda
    0.08
    Act Density 0.022%

    No Known Activations