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

    Neuronpedia

    INDEX
    Explanations

    Revision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    fill
    -0.08
    .Loader
    -0.07
     prefix
    -0.07
    _bm
    -0.07
     الغ
    -0.06
    猃
    -0.06
    偿还
    -0.06
     warmed
    -0.06
     req
    -0.06
    POSITIVE LOGITS
     Jasper
    0.09
     Ian
    0.07
     Retrieves
    0.07
    ISED
    0.07
    Leo
    0.06
     Snape
    0.06
     Jane
    0.06
     plagiarism
    0.06
     Alice
    0.06
    !".
    0.06
    Act Density 0.002%

    No Known Activations