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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    úmero
    -0.07
     reach
    -0.07
     의미
    -0.06
     included
    -0.06
     emulator
    -0.06
    atio
    -0.06
    čka
    -0.06
     neglect
    -0.06
     Dirk
    -0.06
     exclude
    -0.06
    POSITIVE LOGITS
    ":"
    0.06
    /assets
    0.06
    firstname
    0.06
     totalPages
    0.06
     expiresIn
    0.06
    bilir
    0.06
     Rebels
    0.06
     Shakespeare
    0.06
    Nit
    0.06
    _players
    0.06
    Act Density 0.001%

    No Known Activations