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

    Neuronpedia

    INDEX
    Explanations

    new experiences and challenges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kovou
    -0.07
     Gazette
    -0.07
     arguing
    -0.07
     illusion
    -0.06
     poetry
    -0.06
     comentario
    -0.06
     attended
    -0.06
    maze
    -0.06
    :x
    -0.06
    ighest
    -0.06
    POSITIVE LOGITS
     wir
    0.07
     Nike
    0.06
    .AllowGet
    0.06
    ΙΑΚ
    0.06
    .AUTH
    0.06
    .sem
    0.06
     SVM
    0.06
    地區
    0.06
    Restaurant
    0.06
    _AREA
    0.06
    Act Density 0.172%

    No Known Activations