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

    Neuronpedia

    INDEX
    Explanations

    resulting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dream
    -0.07
    _boost
    -0.07
    �
    -0.07
    customers
    -0.06
     高
    -0.06
    more
    -0.06
    oltage
    -0.06
    span
    -0.06
    Doctor
    -0.06
     přátel
    -0.06
    POSITIVE LOGITS
     nejsou
    0.07
     profiling
    0.07
     필
    0.07
    ้↵
    0.06
    کور
    0.06
     glGet
    0.06
    */,↵
    0.06
    ...
↵
    0.06
     dvoj
    0.06
     prior
    0.06
    Act Density 0.012%

    No Known Activations