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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datasets
    -0.07
    Elim
    -0.06
     rowspan
    -0.06
     즉
    -0.06
    하였다
    -0.06
     Sandra
    -0.06
     �
    -0.06
     Retrie
    -0.06
    udoku
    -0.06
    esterday
    -0.06
    POSITIVE LOGITS
     München
    0.07
    oen
    0.07
     JsonRequestBehavior
    0.06
    .ac
    0.06
    -В
    0.06
    741
    0.06
    атель
    0.06
     Buff
    0.06
     RCMP
    0.06
    .vocab
    0.06
    Act Density 0.016%

    No Known Activations