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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sillons
    0.64
     bâtiments
    0.64
    onnés
    0.64
    𝑻
    0.60
    ționale
    0.58
    𝑫
    0.58
    tfine
    0.57
     લા
    0.57
    0.57
    0.56
    POSITIVE LOGITS
     col
    0.71
     COL
    0.65
     Colin
    0.64
     Colbert
    0.63
     Exodus
    0.63
     Mark
    0.62
     King
    0.62
     Henry
    0.62
     Colo
    0.62
     Saka
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.