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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PureComponent
    -0.07
     �
    -0.06
    율
    -0.06
     різних
    -0.06
     расп
    -0.06
    Pes
    -0.06
     Fakültesi
    -0.06
     busted
    -0.06
     podmínek
    -0.06
    (payload
    -0.06
    POSITIVE LOGITS
     while
    0.07
     whereas
    0.06
     tales
    0.06
     rows
    0.06
     lies
    0.06
    lie
    0.06
     Wright
    0.06
    place
    0.06
                              ↵
    0.06
    اخته
    0.06
    Act Density 0.021%

    No Known Activations