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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iant
    -0.07
    SSFWorkbook
    -0.07
     Alerts
    -0.06
     부탁
    -0.06
     trùng
    -0.06
    NSNotification
    -0.06
    01
    -0.06
    �
    -0.06
    速
    -0.06
     mailing
    -0.06
    POSITIVE LOGITS
    _region
    0.07
    erseniz
    0.06
     Alexandria
    0.06
     annihil
    0.06
    ινε
    0.06
    enuine
    0.06
    čin
    0.06
     durumlarda
    0.06
    λε
    0.06
     yoktur
    0.06
    Act Density 0.002%

    No Known Activations