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

    Neuronpedia

    INDEX
    Explanations

    underlie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    組
    -0.07
     ware
    -0.07
     bay
    -0.07
    Л
    -0.07
    宮
    -0.07
     violet
    -0.07
     Lightning
    -0.06
     jack
    -0.06
     probe
    -0.06
     робот
    -0.06
    POSITIVE LOGITS
    اگ
    0.07
    [at
    0.06
    @endsection
    0.06
    _FOUND
    0.06
     getBy
    0.06
    otřeb
    0.06
    _NOTICE
    0.06
     exceedingly
    0.06
    ậy
    0.06
    ância
    0.05
    Act Density 0.019%

    No Known Activations