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

    Neuronpedia

    INDEX
    Explanations

    additions and changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machen
    -0.07
     emple
    -0.06
    Ale
    -0.06
     Pon
    -0.06
    함
    -0.06
    еф
    -0.06
     Athen
    -0.06
    Strings
    -0.06
    ?>&
    -0.06
    _processors
    -0.06
    POSITIVE LOGITS
     Maj
    0.07
     strengthens
    0.07
     kry
    0.06
     právo
    0.06
     Deals
    0.06
    ADMIN
    0.06
     distinctly
    0.06
     embry
    0.06
    \Helpers
    0.06
     cath
    0.06
    Act Density 0.013%

    No Known Activations