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

    Neuronpedia

    INDEX
    Explanations

    contour ants

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alfabet
    0.74
     Shub
    0.74
     коопера
    0.66
    form
    0.65
    plete
    0.62
    mathemat
    0.62
     உள்ள
    0.62
     কল্যাণ
    0.62
     রেশন
    0.62
     matematik
    0.61
    POSITIVE LOGITS
     ant
    0.69
     contour
    0.68
    が無
    0.68
    தல
    0.64
     Contour
    0.64
     personally
    0.64
     Bxe
    0.63
     ants
    0.62
    contour
    0.62
    Labs
    0.61
    Act Density 0.028%

    No Known Activations