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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sext
    -0.07
    (IB
    -0.06
    .plugins
    -0.06
     вход
    -0.06
    Seat
    -0.06
    .part
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     interfaces
    -0.06
    .showToast
    -0.06
     km
    -0.06
    POSITIVE LOGITS
     دانشنامه
    0.07
    '};↵
    0.06
     üy
    0.06
    George
    0.06
    照
    0.06
     SAN
    0.06
    aac
    0.06
     clauses
    0.06
     Panama
    0.06
     subdiv
    0.06
    Act Density 0.002%

    No Known Activations