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

    Neuronpedia

    INDEX
    Explanations

    authority figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sessions
    -0.07
    χεία
    -0.06
     всех
    -0.06
    /System
    -0.06
     услов
    -0.06
     становится
    -0.06
    Materials
    -0.06
    什
    -0.06
     corrid
    -0.06
     dirs
    -0.06
    POSITIVE LOGITS
     بوابة
    0.07
    Done
    0.06
    Chem
    0.06
    .loggedIn
    0.06
     Extr
    0.06
    iqu
    0.06
     outweigh
    0.06
    ulos
    0.06
    inand
    0.06
    Hand
    0.06
    Act Density 0.046%

    No Known Activations