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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guinness
    -0.07
     Lawyers
    -0.07
    ilyn
    -0.07
    uco
    -0.07
     Fiction
    -0.06
    Authors
    -0.06
     mph
    -0.06
     Plaza
    -0.06
     unusual
    -0.06
    ůležit
    -0.06
    POSITIVE LOGITS
     студ
    0.07
     bonne
    0.07
    �
    0.07
     journalistic
    0.06
    _ANGLE
    0.06
    沒
    0.06
     Armenia
    0.06
     bona
    0.06
     Charl
    0.06
     flam
    0.06
    Act Density 0.403%

    No Known Activations