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

    Neuronpedia

    INDEX
    Explanations

    University

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ty
    -0.06
     toll
    -0.06
     бы
    -0.06
    -at
    -0.06
    اشت
    -0.06
    orage
    -0.06
     kon
    -0.06
    Công
    -0.06
    _closure
    -0.06
     hale
    -0.06
    POSITIVE LOGITS
     Buckingham
    0.15
     definitive
    0.11
     Yugoslavia
    0.10
    \HttpFoundation
    0.10
     Yugosl
    0.09
     FIFA
    0.08
     UEFA
    0.08
    ัตว
    0.07
    (intent
    0.07
    entin
    0.07
    Act Density 0.004%

    No Known Activations