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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erais
    -0.06
     zku
    -0.06
    よ
    -0.06
    master
    -0.06
    ulist
    -0.06
     wiel
    -0.06
     CEOs
    -0.06
     litter
    -0.06
     cryst
    -0.06
     durante
    -0.06
    POSITIVE LOGITS
    τευ
    0.07
    ,test
    0.06
    POSITION
    0.06
    ,s
    0.06
    ]==
    0.06
    úsqueda
    0.06
    ,message
    0.06
     Κατηγορία
    0.06
    _EN
    0.06
    accuracy
    0.06
    Act Density 0.006%

    No Known Activations