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

    Neuronpedia

    INDEX
    Explanations

    not well understood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Morning
    -0.07
     Brunswick
    -0.07
     tout
    -0.07
     Morning
    -0.06
     purchases
    -0.06
    (BuildContext
    -0.06
     nan
    -0.06
     февра
    -0.06
    orsk
    -0.06
     Zone
    -0.06
    POSITIVE LOGITS
    CREASE
    0.07
     sle
    0.07
    _led
    0.07
    auer
    0.06
    INDER
    0.06
     изб
    0.06
     Definitely
    0.06
    yper
    0.06
    _properties
    0.06
    .stat
    0.06
    Act Density 0.019%

    No Known Activations