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

    Neuronpedia

    INDEX
    Explanations

    Code or software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Personen
    -0.07
     camper
    -0.07
     continue
    -0.07
     Facebook
    -0.07
    :
↵
↵
    -0.07
    司机
    -0.07
    燃气
    -0.07
     violent
    -0.07
    手机号
    -0.06
    Credits
    -0.06
    POSITIVE LOGITS
    婀
    0.07
     Cuban
    0.07
    ‶
    0.07
     SWT
    0.07
    _TRIGGER
    0.07
    _GU
    0.06
    assoc
    0.06
     Austral
    0.06
     Dodd
    0.06
    .mar
    0.06
    Act Density 0.041%

    No Known Activations