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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Economics
    -0.07
     Executors
    -0.07
    _keyboard
    -0.07
    izioni
    -0.06
    Ticker
    -0.06
    经
    -0.06
     Alarm
    -0.06
    369
    -0.06
    Submission
    -0.06
    有限
    -0.06
    POSITIVE LOGITS
     instruct
    0.07
    _BOOL
    0.06
     underestimated
    0.06
     Mund
    0.06
     порядку
    0.06
     camper
    0.06
    |(↵
    0.06
     )↵↵
    0.06
     snacks
    0.06
    ussed
    0.06
    Act Density 0.002%

    No Known Activations