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

    Neuronpedia

    INDEX
    Explanations

    COUNT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     što
    -0.07
     burgeoning
    -0.06
     foyer
    -0.06
    냐
    -0.06
    King
    -0.06
    Persistence
    -0.06
    adık
    -0.06
     antibiot
    -0.06
    yect
    -0.06
    feeds
    -0.06
    POSITIVE LOGITS
    andom
    0.07
     Ye
    0.06
    (program
    0.06
    _temperature
    0.06
     Arizona
    0.06
    izzie
    0.06
    awaii
    0.06
     Venezuel
    0.06
     Amanda
    0.06
    }})↵
    0.06
    Act Density 0.003%

    No Known Activations